Publications (180)
Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks
Yixin Cao, Shibo Hong, Xinze Li +24
Large Language Models (LLMs) are advancing at an amazing speed and have become indispensable across academia, industry, and daily applications. To keep pace with the status quo, th…
Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models
Xueqi Ma, Xingjun Ma, Sarah Monazam Erfani +2
Developing open-set classification methods capable of classifying in-distribution (ID) data while detecting out-of-distribution (OOD) samples is essential for deploying graph neura…
Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models
Yang Bai, Ge Pei, Jindong Gu +2
Large language models (LLMs) have achieved remarkable performance on a wide range of tasks. However, recent studies have shown that LLMs can memorize training data and simple repea…
Clean-Label Backdoor Attacks on Video Recognition Models
Shihao Zhao, Xingjun Ma, Xiang Zheng +3
Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean tes…
Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
Xueqi Ma, Shuo Yang, Yanbei Jiang +6
Despite remarkable advances in large Vision-Language Models (VLMs), spatial reasoning remains a persistent challenge. In this work, we investigate how attention heads within VLMs c…
Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models
Tianyi Lu, Xing Zhang, Jiaxi Gu +5
Latent Diffusion Models (LDMs) are renowned for their powerful capabilities in image and video synthesis. Yet, compared to text-to-image (T2I) editing, text-to-video (T2V) editing…
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Yunhao Chen, Xin Wang, Juncheng Li +5
Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space…
On the Convergence and Robustness of Adversarial Training
Yisen Wang, Xingjun Ma, James Bailey +3
Improving the robustness of deep neural networks (DNNs) to adversarial examples is an important yet challenging problem for secure deep learning. Across existing defense techniques…
Normalized Loss Functions for Deep Learning with Noisy Labels
Xingjun Ma, Hanxun Huang, Yisen Wang +3
Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross En…
Imperceptible Jailbreaking against Large Language Models
Kuofeng Gao, Yiming Li, Chao Du +4
Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visi…
Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
Jiabo He, Sarah Erfani, Xingjun Ma +3
Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most commonly used loss functions for bbox regression are the Intersection over Union (IoU) los…
AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning
Xin Wang, Kai Chen, Xingjun Ma +3
Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks even under a black-box setting where the adversary can only query the model. Particularly, query-based…
On the Importance of Spatial Relations for Few-shot Action Recognition
Yilun Zhang, Yuqian Fu, Xingjun Ma +4
Deep learning has achieved great success in video recognition, yet still struggles to recognize novel actions when faced with only a few examples. To tackle this challenge, few-sho…
DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
Zonghuan Xu, Jiayu Li, Yunhan Zhao +3
Vision-Language-Action (VLA) models map multimodal perception and language instructions to executable robot actions, making them particularly vulnerable to behavioral backdoor mani…
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
Hanxun Huang, Sarah Erfani, Yige Li +2
As Contrastive Language-Image Pre-training (CLIP) models are increasingly adopted for diverse downstream tasks and integrated into large vision-language models (VLMs), their suscep…
Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks
Hanxun Huang, Yisen Wang, Sarah Monazam Erfani +3
Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of defense methods have been proposed to train adversarially robust DNNs, among which adversa…
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
Jiaqi Yu, Xin Wang, Yixu Wang +4
Large language models increasingly stream long, reasoning-intensive responses in real time, making when to moderate as critical as whether to moderate. Existing guardrails fall int…
When Direct Prediction Fails: Evidence from LLM-Based Misinformation Risk Evaluation
Zonghuan Xu, Xiang Zheng, Yutao Wu +1
LLMs make it increasingly easy to generate deceptive content at scale, creating a need for scalable misinformation risk evaluation based on whether readers find such content credib…
Reconstructive Neuron Pruning for Backdoor Defense
Yige Li, Xixiang Lyu, Xingjun Ma +4
Deep neural networks (DNNs) have been found to be vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. While existing…
PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading
Yutao Wu, Xiao Liu, Yunhao Feng +2
Large Language Models (LLMs) increasingly serve as research assistants, yet their reliability in scholarly tasks remains under-evaluated. In this work, we introduce PaperAsk, a ben…
AutoBackdoor: Automating Backdoor Attacks via LLM Agents
Yige Li, Zhe Li, Wei Zhao +4
Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. Howe…
LDReg: Local Dimensionality Regularized Self-Supervised Learning
Hanxun Huang, Ricardo J. G. B. Campello, Sarah Monazam Erfani +3
Representations learned via self-supervised learning (SSL) can be susceptible to dimensional collapse, where the learned representation subspace is of extremely low dimensionality…
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Kun Wang, Guibin Zhang, Zhenhong Zhou +100
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communi…
Anomaly Detection for Scenario-based Insider Activities using CGAN Augmented Data
R G Gayathri, Atul Sajjanhar, Yong Xiang +1
Insider threats are the cyber attacks from within the trusted entities of an organization. Lack of real-world data and issue of data imbalance leave insider threat analysis an unde…
Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy
Xiang Zheng, Xingjun Ma, Shengjie Wang +3
Reinforcement learning agents are susceptible to evasion attacks during deployment. In single-agent environments, these attacks can occur through imperceptible perturbations inject…
Backdoor Attacks on Time Series: A Generative Approach
Yujing Jiang, Xingjun Ma, Sarah Monazam Erfani +1
Backdoor attacks have emerged as one of the major security threats to deep learning models as they can easily control the model's test-time predictions by pre-injecting a backdoor…
Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models
Jialuo Chen, Jingyi Wang, Tinglan Peng +6
Deep learning (DL) models, especially those large-scale and high-performance ones, can be very costly to train, demanding a great amount of data and computational resources. Unauth…
CALM: Curiosity-Driven Auditing for Large Language Models
Xiang Zheng, Longxiang Wang, Yi Liu +3
Auditing Large Language Models (LLMs) is a crucial and challenging task. In this study, we focus on auditing black-box LLMs without access to their parameters, only to the provided…
Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
Weijie Zheng, Xingjun Ma, Hanxun Huang +2
With the advancement of vision transformers (ViTs) and self-supervised learning (SSL) techniques, pre-trained large ViTs have become the new foundation models for computer vision a…
Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models
Zezhou Wang, Yaxin Du, Xingjun Ma +3
Federated domain-specific instruction tuning (FedDIT) for large language models (LLMs) aims to enhance performance in specialized domains using distributed private and limited data…
Towards Context-Invariant Safety Alignment for Large Language Models
Yixu Wang, Yang Yao, Xin Wang +4
Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a standard prompt but comply when t…
White-box Multimodal Jailbreaks Against Large Vision-Language Models
Ruofan Wang, Xingjun Ma, Hanxu Zhou +3
Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been…
VeriFi: Towards Verifiable Federated Unlearning
Xiangshan Gao, Xingjun Ma, Jingyi Wang +5
Federated learning (FL) is a collaborative learning paradigm where participants jointly train a powerful model without sharing their private data. One desirable property for FL is…
OmniSVG: A Unified Scalable Vector Graphics Generation Model
Yiying Yang, Wei Cheng, Sijin Chen +7
Scalable Vector Graphics (SVG) is an important image format widely adopted in graphic design because of their resolution independence and editability. The study of generating high-…
RobOT: Robustness-Oriented Testing for Deep Learning Systems
Jingyi Wang, Jialuo Chen, Youcheng Sun +4
Recently, there has been a significant growth of interest in applying software engineering techniques for the quality assurance of deep learning (DL) systems. One popular direction…
From Order to Distribution: A Spectral Characterization of Forgetting in Continual Learning
Zonghuan Xu, Xingjun Ma
A central challenge in continual learning is forgetting, the loss of performance on previously learned tasks induced by sequential adaptation to new ones. While forgetting has been…
RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
Ruofan Wang, Xingjun Ma
Large Vision-Language Models (VLMs) are increasingly deployed in open-ended environments, where ensuring reliable safety under multimodal inputs is critical. However, existing eval…
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
Xiao Li, Xiang Zheng, Yifeng Gao +35
Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As…
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
Yige Li, Wei Zhao, Zhe Li +6
Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional act…
DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning
Yifeng Gao, Yifan Ding, Hongyu Su +9
As AI-generated video becomes increasingly pervasive across media platforms, the ability to reliably distinguish synthetic content from authentic footage has become both urgent and…
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
Zhiyuan Zhang, Lingjuan Lyu, Xingjun Ma +2
Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a larg…
Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
Jiaming Zhang, Boyang Chen, Zherui Li +14
Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technica…
Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples
Jiaming Zhang, Xingjun Ma, Qi Yi +4
There is a growing interest in developing unlearnable examples (UEs) against visual privacy leaks on the Internet. UEs are training samples added with invisible but unlearnable noi…
Providing Effective Real-time Feedback in Simulation-based Surgical Training
Xingjun Ma, Sudanthi Wijewickrema, Yun Zhou +3
Virtual reality simulation is becoming popular as a training platform in surgical education. However, one important aspect of simulation-based surgical training that has not receiv…
A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models
Xincheng Shuai, Henghui Ding, Xingjun Ma +3
Image editing aims to edit the given synthetic or real image to meet the specific requirements from users. It is widely studied in recent years as a promising and challenging field…
Fake Alignment: Are LLMs Really Aligned Well?
Yixu Wang, Yan Teng, Kexin Huang +7
The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored is…
On the Adversarial Transferability of Generalized "Skip Connections"
Yisen Wang, Yichuan Mo, Dongxian Wu +3
Skip connection is an essential ingredient for modern deep models to be deeper and more powerful. Despite their huge success in normal scenarios (state-of-the-art classification pe…
Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
Yunhan Zhao, Xiang Zheng, Xingjun Ma
Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, thei…
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
Yige Li, Hanxun Huang, Jiaming Zhang +2
Backdoor attacks covertly implant triggers into deep neural networks (DNNs) by poisoning a small portion of the training data with pre-designed backdoor triggers. This vulnerabilit…
Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
Kaiyuan Cui, Yige Li, Yutao Wu +4
Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text. However, this multimodal integ…
EventHallusion: Diagnosing Event Hallucinations in Video LLMs
Jiacheng Zhang, Yang Jiao, Shaoxiang Chen +5
Recently, Multimodal Large Language Models (MLLMs) have made significant progress in the video comprehension field. Despite remarkable content reasoning and instruction following c…
UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
Ye Sun, Hao Zhang, Tiehua Zhang +2
Image segmentation is a crucial vision task that groups pixels within an image into semantically meaningful segments, which is pivotal in obtaining a fine-grained understanding of…
Identity Lock: Locking API Fine-tuned LLMs With Identity-based Wake Words
Hongyu Su, Yifeng Gao, Yifan Ding +1
The rapid advancement of Large Language Models (LLMs) has increased the complexity and cost of fine-tuning, leading to the adoption of API-based fine-tuning as a simpler and more e…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…
When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries
Yige Li, Jun Sun, Wei Zhao +5
Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood. We introduce…
Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with constraints
Zhenyun Yin, Shujie Wang, Xuhong Wang +2
Improving the reliability of large language models (LLMs) is critical for deploying them in real-world scenarios. In this paper, we propose \textbf{Deliberative Searcher}, the firs…
Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles
Ranjie Duan, Xingjun Ma, Yisen Wang +3
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. Existing works have mostly focused on either digital adversarial examples created via small and impe…
Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation
Xincheng Shuai, Henghui Ding, Zhenyuan Qin +3
Controlling the movements of dynamic objects and the camera within generated videos is a meaningful yet challenging task. Due to the lack of datasets with comprehensive 6D pose ann…
RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models
Jiale Ding, Xiang Zheng, Yutao Wu +5
As large language models (LLMs) are increasingly deployed as black-box components in real-world applications, red teaming has become essential for identifying potential risks. It t…
Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
Yige Li, Jiabo He, Hanxun Huang +3
Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor…
From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving
Xinyu Xia, Xingjun Ma, Yunfeng Hu +3
Ensuring robust and generalizable autonomous driving requires not only broad scenario coverage but also efficient repair of failure cases, particularly those related to challenging…
Generative Image Inpainting with Submanifold Alignment
Ang Li, Jianzhong Qi, Rui Zhang +2
Image inpainting aims at restoring missing regions of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based generat…
Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better
Bojia Zi, Shihao Zhao, Xingjun Ma +1
Adversarial training is one effective approach for training robust deep neural networks against adversarial attacks. While being able to bring reliable robustness, adversarial trai…
FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
Kun Zhai, Siheng Chen, Xingjun Ma +1
Federated Prompt Tuning (FPT) is an efficient method for cross-client collaborative fine-tuning of large Vision-Language Models (VLMs). However, models tuned using FPT are vulnerab…
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
Yunfei Liu, Xingjun Ma, James Bailey +1
Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a back…
Practical Privacy Attacks on Vertical Federated Learning
Haiqin Weng, Juntao Zhang, Xingjun Ma +4
Federated learning (FL) is a privacy-preserving learning paradigm that allows multiple parities to jointly train a powerful machine learning model without sharing their private dat…
ModelLock: Locking Your Model With a Spell
Yifeng Gao, Yuhua Sun, Xingjun Ma +2
This paper presents a novel model protection paradigm ModelLock that locks (destroys) the performance of a model on normal clean data so as to make it unusable or unextractable wit…
Internal Safety Collapse in Frontier Large Language Models
Yutao Wu, Xiao Liu, Yifeng Gao +7
This work identifies a critical failure mode in frontier large language models (LLMs), which we term Internal Safety Collapse (ISC): under certain task conditions, models enter a s…
AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
Yixu Wang, Xin Wang, Yang Yao +5
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-e…
Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation
Jinze Wang, Lu Zhang, Yiyang Cui +5
Next point-of-interest (POI) recommendation is a key component of smart urban services, yet it remains challenging under cold-start conditions with sparse user-POI interactions. Re…
SIDE: Surrogate Conditional Data Extraction from Diffusion Models
Yunhao Chen, Shujie Wang, Difan Zou +1
As diffusion probabilistic models (DPMs) become central to Generative AI (GenAI), understanding their memorization behavior is essential for evaluating risks such as data leakage,…
Short-Term and Long-Term Context Aggregation Network for Video Inpainting
Ang Li, Shanshan Zhao, Xingjun Ma +5
Video inpainting aims to restore missing regions of a video and has many applications such as video editing and object removal. However, existing methods either suffer from inaccur…
Backdoor Attacks on Crowd Counting
Yuhua Sun, Tailai Zhang, Xingjun Ma +6
Crowd counting is a regression task that estimates the number of people in a scene image, which plays a vital role in a range of safety-critical applications, such as video surveil…
PixelSmile: Toward Fine-Grained Facial Expression Editing
Jiabin Hua, Hengyuan Xu, Aojie Li +4
Fine-grained facial expression editing has long been limited by intrinsic semantic overlap. To address this, we construct the Flex Facial Expression (FFE) dataset with continuous a…
RA-Det: Towards Universal Detection of AI-Generated Images via Robustness Asymmetry
Xinchang Wang, Yunhao Chen, Yuechen Zhang +4
Recent image generators produce photo-realistic content that undermines the reliability of downstream recognition systems. As visual appearance cues become less pronounced, appeara…
Adversarial Prompt Tuning for Vision-Language Models
Jiaming Zhang, Xingjun Ma, Xin Wang +4
With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual…
TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
Xin Wang, Kai Chen, Jiaming Zhang +2
Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have sh…
WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
Bojia Zi, Minghao Chang, Jingjing Chen +2
In recent years, the abuse of a face swap technique called deepfake has raised enormous public concerns. So far, a large number of deepfake videos (known as "deepfakes") have been…
Transferable Unlearnable Examples
Jie Ren, Han Xu, Yuxuan Wan +3
With more people publishing their personal data online, unauthorized data usage has become a serious concern. The unlearnable strategies have been introduced to prevent third parti…
EnJa: Ensemble Jailbreak on Large Language Models
Jiahao Zhang, Zilong Wang, Ruofan Wang +2
As Large Language Models (LLMs) are increasingly being deployed in safety-critical applications, their vulnerability to potential jailbreaks -- malicious prompts that can disable t…
CHASE: A Causal Hypergraph based Framework for Root Cause Analysis in Multimodal Microservice Systems
Ziming Zhao, Zhenwei Wang, Tiehua Zhang +7
In recent years, the widespread adoption of distributed microservice architectures within the industry has significantly increased the demand for enhanced system availability and r…
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
Yunhao Feng, Yifan Ding, Yingshui Tan +6
Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across…
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Ruixiao Lin, Xinhao Deng, Qingming Li +12
Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversa…
CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control
Xiang Zheng, Xingjun Ma, Cong Wang
Intrinsic motivation is a promising exploration technique for solving reinforcement learning tasks with sparse or absent extrinsic rewards. There exist two technical challenges in…
Sub-trajectory Similarity Join with Obfuscation
Yanchuan Chang, Jianzhong Qi, Egemen Tanin +2
User trajectory data is becoming increasingly accessible due to the prevalence of GPS-equipped devices such as smartphones. Many existing studies focus on querying trajectories tha…
Adversarial Generation of Real-time Feedback with Neural Networks for Simulation-based Training
Xingjun Ma, Sudanthi Wijewickrema, Shuo Zhou +4
Simulation-based training (SBT) is gaining popularity as a low-cost and convenient training technique in a vast range of applications. However, for a SBT platform to be fully utili…
Mirror: A Multi-Agent System for AI-Assisted Ethics Review
Yifan Ding, Yuhui Shi, Zhiyan Li +10
Ethics review is a foundational mechanism of modern research governance, yet contemporary systems face increasing strain as ethical risks arise as structural consequences of large-…
Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs
Tiehua Zhang, Yuze Liu, Zhishu Shen +4
Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learni…
Dual Head Adversarial Training
Yujing Jiang, Xingjun Ma, Sarah Monazam Erfani +1
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples/attacks, raising concerns about their reliability in safety-critical applications. A number of defens…
AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
Jiayu Li, Yunhan Zhao, Xiang Zheng +4
Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control i…
FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions
Peng Li, Zihan Zhuang, Yangfan Gao +16
Humanoid robots are capable of performing various actions such as greeting, dancing and even backflipping. However, these motions are often hard-coded or specifically trained, whic…
ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models
Tingshu Mou, Jiabo He, Renying Wang +5
Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leavin…
AudioMosaic: Contrastive Masked Audio Representation Learning
Hanxun Huang, Qizhou Wang, Xingjun Ma +3
Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have been driven mainly by generativ…
Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting
Ang Li, Qiuhong Ke, Xingjun Ma +4
Deep image inpainting aims to restore damaged or missing regions in an image with realistic contents. While having a wide range of applications such as object removal and image rec…
BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
Yunhan Zhao, Xiang Zheng, Lin Luo +3
In this paper, we focus on black-box defense for VLMs against jailbreak attacks. Existing black-box defense methods are either unimodal or bimodal. Unimodal methods enhance either…
Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
Ranjie Duan, Jiexi Liu, Xiaojun Jia +27
Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, of…
Privacy and Robustness in Federated Learning: Attacks and Defenses
Lingjuan Lyu, Han Yu, Xingjun Ma +5
As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (…
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
Yunhao Chen, Xin Wang, Yixu Wang +6
AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior…
Neural Architecture Search via Combinatorial Multi-Armed Bandit
Hanxun Huang, Xingjun Ma, Sarah M. Erfani +1
Neural Architecture Search (NAS) has gained significant popularity as an effective tool for designing high performance deep neural networks (DNNs). NAS can be performed via policy…
ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks
Khondker Fariha Hossain, Sharif Amit Kamran, Alireza Tavakkoli +4
Electrocardiogram (ECG) acquisition requires an automated system and analysis pipeline for understanding specific rhythm irregularities. Deep neural networks have become a popular…