papers

Publications (88)

cs.SE2026

Revisiting the Reliability of Language Models in Instruction-Following

Jianshuo Dong, Yutong Zhang, Yan Liu +4

Advanced LLMs have achieved near-ceiling instruction-following accuracy on benchmarks such as IFEval. However, these impressive scores do not necessarily translate to reliable serv…

cs.CL2025

Speculating LLMs' Chinese Training Data Pollution from Their Tokens

Qingjie Zhang, Di Wang, Haoting Qian +7

Tokens are basic elements in the datasets for LLM training. It is well-known that many tokens representing Chinese phrases in the vocabulary of GPT (4o/4o-mini/o1/o3/4.5/4.1/o4-min…

cs.CR2025

An Engorgio Prompt Makes Large Language Model Babble on

Jianshuo Dong, Ziyuan Zhang, Qingjie Zhang +7

Auto-regressive large language models (LLMs) have yielded impressive performance in many real-world tasks. However, the new paradigm of these LLMs also exposes novel threats. In th…

cs.CV2022

Watermarking Pre-trained Encoders in Contrastive Learning

Yutong Wu, Han Qiu, Tianwei Zhang +2

Contrastive learning has become a popular technique to pre-train image encoders, which could be used to build various downstream classification models in an efficient way. This pro…

cs.CV2023

Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey

Jiaxing Huang, Jingyi Zhang, Kai Jiang +2

Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising tw…

cs.CR2023

Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks

Jialai Wang, Ziyuan Zhang, Meiqi Wang +6

Bit-flip attacks (BFAs) have attracted substantial attention recently, in which an adversary could tamper with a small number of model parameter bits to break the integrity of DNNs…

econ.TH2018

An Inattention Model for Traveler Behavior with e-Coupons

Han Qiu

In this study, we consider traveler coupon redemption behavior from the perspective of an urban mobility service. Assuming traveler behavior is in accordance with the principle of…

cs.CR2023

A Unified Hardware-based Threat Detector for AI Accelerators

Xiaobei Yan, Han Qiu, Tianwei Zhang

The proliferation of AI technology gives rise to a variety of security threats, which significantly compromise the confidentiality and integrity of AI models and applications. Exis…

cs.CL2025

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity

Shiyao Cui, Xijia Feng, Yingkang Wang +6

Emojis are globally used non-verbal cues in digital communication, and extensive research has examined how large language models (LLMs) understand and utilize emojis across context…

cs.CR2023

Mercury: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator

Xiaobei Yan, Xiaoxuan Lou, Guowen Xu +4

DNN accelerators have been widely deployed in many scenarios to speed up the inference process and reduce the energy consumption. One big concern about the usage of the accelerator…

cs.LG2020

FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation Techniques

Han Qiu, Yi Zeng, Tianwei Zhang +2

It is extensively studied that Deep Neural Networks (DNNs) are vulnerable to Adversarial Examples (AEs). With more and more advanced adversarial attack methods have been developed,…

cs.AI2026

Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure

Yida Lu, Jianwei Fang, Xuyang Shao +7

As Large Language Models (LLMs) evolve from chatbots to agentic assistants, they are increasingly observed to exhibit risky behaviors when subjected to survival pressure, such as t…

cs.CV2024

SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution

Runyi Hu, Jie Zhang, Yiming Li +4

In today's digital landscape, the blending of AI-generated and authentic content has underscored the need for copyright protection and content authentication. Watermarking has beco…

cs.CV2024

Learning to Prompt Segment Anything Models

Jiaxing Huang, Kai Jiang, Jingyi Zhang +4

Segment Anything Models (SAMs) like SEEM and SAM have demonstrated great potential in learning to segment anything. The core design of SAMs lies with Promptable Segmentation, which…

cs.CR2026

Can Large Language Models Automate the Refinement of Cellular Network Specifications?

Jianshuo Dong, Yuanjie Li, Jun Liu +2

Cellular networks, e.g., 4G/5G, rely on complex technical specifications to ensure correct functionality; however, these specifications often contain flaws or ambiguities. In this…

cs.ET2024

A Case for Application-Aware Space Radiation Tolerance in Orbital Computing

Meiqi Wang, Han Qiu, Longnv Xu +5

We are witnessing a surge in the use of commercial off-the-shelf (COTS) hardware for cost-effective in-orbit computing, such as deep neural network (DNN) based on-satellite sensor…

cs.CL2026

ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection

Axel Delaval, Shujian Yang, Haicheng Wang +2

Detecting toxic content using language models is crucial yet challenging. While substantial progress has been made in English, toxicity detection in French remains underdeveloped,…

cs.CL2022

An MRC Framework for Semantic Role Labeling

Nan Wang, Jiwei Li, Yuxian Meng +5

Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument label…

cs.AI2026

Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models

Qingjie Zhang, Yujia Fu, Yang Wang +5

Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model's operational capability boundary, lea…

cs.CV2025

Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems

Jie Zhang, Ting Xu, Gelei Deng +5

Writing is a universal cultural technology that reuses vision for symbolic communication. Humans display striking resilience: we readily recognize words even when characters are fr…

cs.CV2025

VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking

Runyi Hu, Jie Zhang, Yiming Li +4

Artificial Intelligence Generated Content (AIGC) has advanced significantly, particularly with the development of video generation models such as text-to-video (T2V) models and ima…

cs.CR2019

TEST: an End-to-End Network Traffic Examination and Identification Framework Based on Spatio-Temporal Features Extraction

Yi Zeng, Zihao Qi, Wencheng Chen +3

With more encrypted network traffic gets involved in the Internet, how to effectively identify network traffic has become a top priority in the field. Accurate identification of th…

cs.CV2026

The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning

Renmiao Chen, Yida Lu, Shiyao Cui +6

As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We stud…

cs.LG2018

Learning Correlation Space for Time Series

Han Qiu, Hoang Thanh Lam, Francesco Fusco +1

We propose an approximation algorithm for efficient correlation search in time series data. In our method, we use Fourier transform and neural network to embed time series into a l…

cs.CR2022

jTrans: Jump-Aware Transformer for Binary Code Similarity

Hao Wang, Wenjie Qu, Gilad Katz +5

Binary code similarity detection (BCSD) has important applications in various fields such as vulnerability detection, software component analysis, and reverse engineering. Recent s…

cs.AI2026

Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness

Haoting Qian, Qingjie Zhang, Zhicong Huang +2

Benchmarking machine unlearning methods is critical to understand whether sensitive knowledge is removed from large language models (LLMs) or not. Current unlearning benchmarks inc…

cs.CR2022

Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing

Tian Dong, Ziyuan Zhang, Han Qiu +3

Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing…

cs.AI2025

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning

Guanlin Li, Kangjie Chen, Shangwei Guo +6

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-sp…

cs.NI2024

Operationalizing AI in Future Networks: A Bird's Eye View from the System Perspective

Qiong Liu, Tianzhu Zhang, Masoud Hemmatpour +5

Modern Artificial Intelligence (AI) technologies, led by Machine Learning (ML), have gained unprecedented momentum over the past decade. Following this wave of "AI summer", the net…

cs.AI2026

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents

Jianshuo Dong, Sheng Guo, Hao Wang +6

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search r…

cs.LG2026

Physiologically Informed Deep Learning: A Multi-Scale Framework for Next-Generation PBPK Modeling

Shunqi Liu, Han Qiu, Tong Wang

Physiologically Based Pharmacokinetic (PBPK) modeling is a cornerstone of model-informed drug development (MIDD), providing a mechanistic framework to predict drug absorption, dist…

cs.CR2024

Fingerprinting Image-to-Image Generative Adversarial Networks

Guanlin Li, Guowen Xu, Han Qiu +5

Generative Adversarial Networks (GANs) have been widely used in various application scenarios. Since the production of a commercial GAN requires substantial computational and human…

cs.CV2026

EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models

Shiqi Huang, Ziyue Wang, Zhongrong Zuo +3

Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL). However, existing RL pipelines rely he…

cs.IR2022

System Log Parsing: A Survey

Tianzhu Zhang, Han Qiu, Gabriele Castellano +3

Modern information and communication systems have become increasingly challenging to manage. The ubiquitous system logs contain plentiful information and are thus widely exploited…

cs.CV2026

SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models

Renyang Liu, Kangjie Chen, Han Qiu +4

Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from their training data, leading to…

cs.CL2025

Understanding the Dark Side of LLMs' Intrinsic Self-Correction

Qingjie Zhang, Di Wang, Haoting Qian +7

Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic se…

cs.CL2024

Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias

Rongwu Xu, Zi'an Zhou, Tianwei Zhang +5

The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access t…

cs.CV2024

Masked AutoDecoder is Effective Multi-Task Vision Generalist

Han Qiu, Jiaxing Huang, Peng Gao +3

Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers…

cs.CV2023

Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation

Jiaxing Huang, Jingyi Zhang, Han Qiu +2

Traditional domain adaptation assumes the same vocabulary across source and target domains, which often struggles with limited transfer flexibility and efficiency while handling ta…

cs.CR2019

Privacy-preserving Health Data Sharing for Medical Cyber-Physical Systems

Han Qiu, Meikang Qiu, Meiqin Liu +1

The recent spades of cyber security attacks have compromised end users' data safety and privacy in Medical Cyber-Physical Systems (MCPS). Traditional standard encryption algorithms…

cs.CR2022

An Interpretable Federated Learning-based Network Intrusion Detection Framework

Tian Dong, Song Li, Han Qiu +1

Learning-based Network Intrusion Detection Systems (NIDSs) are widely deployed for defending various cyberattacks. Existing learning-based NIDS mainly uses Neural Network (NN) as a…

cs.CL2021

Interpreting Deep Learning Models in Natural Language Processing: A Review

Xiaofei Sun, Diyi Yang, Xiaoya Li +6

Neural network models have achieved state-of-the-art performances in a wide range of natural language processing (NLP) tasks. However, a long-standing criticism against neural netw…

cs.CR2021

DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation

Han Qiu, Yi Zeng, Shangwei Guo +3

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However…

cs.LG2023

Rethinking Adversarial Training with Neural Tangent Kernel

Guanlin Li, Han Qiu, Shangwei Guo +2

Adversarial training (AT) is an important and attractive topic in deep learning security, exhibiting mysteries and odd properties. Recent studies of neural network training dynamic…

cs.CL2025

Understanding the Dilemma of Unlearning for Large Language Models

Qingjie Zhang, Haoting Qian, Zhicong Huang +5

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered…

cs.CR2026

What Makes a Good LLM Agent for Real-world Penetration Testing?

Gelei Deng, Yi Liu, Yuekang Li +5

LLM-based agents show promise for automating penetration testing, yet reported performance varies widely across systems and benchmarks. We analyze 28 LLM-based penetration testing…

cs.CV2023

SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models

Ziyi Lin, Chris Liu, Renrui Zhang +13

We present SPHINX, a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, tuning tasks, and visual embeddings. First, for stronger vision-languag…

cs.CR2021

Fingerprinting Multi-exit Deep Neural Network Models via Inference Time

Tian Dong, Han Qiu, Tianwei Zhang +3

Transforming large deep neural network (DNN) models into the multi-exit architectures can overcome the overthinking issue and distribute a large DNN model on resource-constrained s…

cs.CR2020

A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks

Yi Zeng, Han Qiu, Gerard Memmi +1

Deep Neural Networks (DNNs) in Computer Vision (CV) are well-known to be vulnerable to Adversarial Examples (AEs), namely imperceptible perturbations added maliciously to cause wro…

cs.CL2024

The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation

Rongwu Xu, Brian S. Lin, Shujian Yang +6

Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility beha…

cs.CV2019

A Fine-Grained Facial Expression Database for End-to-End Multi-Pose Facial Expression Recognition

Wenxuan Wang, Qiang Sun, Tao Chen +5

The recent research of facial expression recognition has made a lot of progress due to the development of deep learning technologies, but some typical challenging problems such as…

cs.CV2025

Spatial Preference Rewarding for MLLMs Spatial Understanding

Han Qiu, Peng Gao, Lewei Lu +3

Multimodal large language models~(MLLMs) have demonstrated promising spatial understanding capabilities, such as referencing and grounding object descriptions. Despite their succes…

cs.CV2024

LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language Models

Han Qiu, Jiaxing Huang, Peng Gao +4

Hallucination, a phenomenon where multimodal large language models~(MLLMs) tend to generate textual responses that are plausible but unaligned with the image, has become one major…

cs.CL2025

Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs

Jiawei Kong, Hao Fang, Xiaochen Yang +5

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revis…

eess.IV2024

COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation

Ziyuan Zhang, Han Qiu, Maosen Zhang +4

With the rapidly increasing number of satellites in space and their enhanced capabilities, the amount of earth observation images collected by satellites is exceeding the transmiss…

eess.IV2020

Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques

Qinkai Zheng, Han Qiu, Gerard Memmi +1

This is the report for the PRIM project in Telecom Paris. This report is about applications based on spatial-frequency transform and deep learning techniques. In this report, there…

cs.LG2023

Omnipotent Adversarial Training in the Wild

Guanlin Li, Kangjie Chen, Yuan Xu +2

Adversarial training is an important topic in robust deep learning, but the community lacks attention to its practical usage. In this paper, we aim to resolve a real-world challeng…

cs.CV2026

Video-KTR: Reinforcing Video Reasoning via Key Token Attribution

Ziyue Wang, Sheng Jin, Zhongrong Zuo +5

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video reasoning methods often rely on coarse sequen…

cs.CV2025

MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection

Renrui Zhang, Han Qiu, Tai Wang +7

Monocular 3D object detection has long been a challenging task in autonomous driving. Most existing methods follow conventional 2D detectors to first localize object centers, and t…

cs.CV2021

BorderDet: Border Feature for Dense Object Detection

Han Qiu, Yuchen Ma, Zeming Li +2

Dense object detectors rely on the sliding-window paradigm that predicts the object over a regular grid of image. Meanwhile, the feature maps on the point of the grid are adopted t…

cs.SE2024

CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity Detection

Hao Wang, Zeyu Gao, Chao Zhang +4

Binary code similarity detection (BCSD) is a fundamental technique for various application. Many BCSD solutions have been proposed recently, which mostly are embedding-based, but h…

math.OC2018

Dynamic Pricing in Shared Mobility on Demand Service

Han Qiu, Ruimin Li, Jinhua Zhao

We consider a profit maximization problem in an urban mobility on-demand service, of which the operator owns a fleet, provides both exclusive and shared trip services, and dynamica…

cs.CV2025

Mask Image Watermarking

Runyi Hu, Jie Zhang, Shiqian Zhao +5

We present MaskWM, a simple, efficient, and flexible framework for image watermarking. MaskWM has two variants: (1) MaskWM-D, which supports global watermark embedding, watermark l…

cs.CR2025

ObfusBFA: A Holistic Approach to Safeguarding DNNs from Different Types of Bit-Flip Attacks

Xiaobei Yan, Han Qiu, Tianwei Zhang

Bit-flip attacks (BFAs) represent a serious threat to Deep Neural Networks (DNNs), where flipping a small number of bits in the model parameters or binary code can significantly de…

cs.CR2026

State-Dependent Safety Failures in Multi-Turn Language Model Interaction

Pengcheng Li, Jie Zhang, Tianwei Zhang +5

Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically…

cs.CR2023

One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training

Jianshuo Dong, Han Qiu, Yiming Li +5

Deep neural networks (DNNs) are widely deployed on real-world devices. Concerns regarding their security have gained great attention from researchers. Recently, a new weight modifi…

cs.CR2018

An Efficient Data Protection Architecture Based on Fragmentation and Encryption

Han Qiu

In this thesis, a completely revisited data protection scheme based on selective encryption is presented. First, this new scheme is agnostic in term of data format, second it has a…

cs.CR2026

BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models

Xiaobei Yan, Yiming Li, Hao Wang +2

Large language models (LLMs) are widely deployed, but their substantial compute demands make them vulnerable to inference cost attacks that aim to deliberately maximize the output…

cs.CR2017

Data Protection: Combining Fragmentation, Encryption, and Dispersion, a final report

Gerard Memmi, Katarzyna Kapusta, Patrick Lambein +1

Hardening data protection using multiple methods rather than 'just' encryption is of paramount importance when considering continuous and powerful attacks in order to observe, stea…

cs.LG2026

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Junxiao Yang, Haoran Liu, Jinzhe Tu +9

Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We a…

cs.CR2021

Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models

Shangwei Guo, Tianwei Zhang, Han Qiu +3

Watermarking has become the tendency in protecting the intellectual property of DNN models. Recent works, from the adversary's perspective, attempted to subvert watermarking mechan…

cs.CV2025

Warfare:Breaking the Watermark Protection of AI-Generated Content

Guanlin Li, Yifei Chen, Jie Zhang +5

AI-Generated Content (AIGC) is rapidly expanding, with services using advanced generative models to create realistic images and fluent text. Regulating such content is crucial to p…

cs.CR2026

LeakDojo: Decoding the Leakage Threats of RAG Systems

Maosen Zhang, Jianshuo Dong, Boting Lu +4

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to leverage external knowledge, but also exposes valuable RAG databases to leakage attacks. As RAG systems…

cs.CR2025

DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling

Boheng Li, Junjie Wang, Yiming Li +7

Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or viole…

cs.CL2025

Towards Understanding the Cognitive Habits of Large Reasoning Models

Jianshuo Dong, Yujia Fu, Chuanrui Hu +2

Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain of Thought (CoT) before producing final responses, offer a promising approach to interpreting and monito…

cs.CR2026

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models

Haoran Ou, Kangjie Chen, Xingshuo Han +4

Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date information from the open Inte…

cs.CR2020

Mitigating Advanced Adversarial Attacks with More Advanced Gradient Obfuscation Techniques

Han Qiu, Yi Zeng, Qinkai Zheng +3

Deep Neural Networks (DNNs) are well-known to be vulnerable to Adversarial Examples (AEs). A large amount of efforts have been spent to launch and heat the arms race between the at…

cs.AI2026

Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking

Haoran Ou, Gelei Deng, Xingshuo Han +4

The increasing multimodal disinformation, where deceptive claims are reinforced through coordinated text and visual content, poses significant challenges to automated fact-checking…

cs.CV2020

Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition

Wenxuan Wang, Yanwei Fu, Qiang Sun +7

Affective computing and cognitive theory are widely used in modern human-computer interaction scenarios. Human faces, as the most prominent and easily accessible features, have att…

cs.CL2024

Course-Correction: Safety Alignment Using Synthetic Preferences

Rongwu Xu, Yishuo Cai, Zhenhong Zhou +6

The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability…

cs.MM2025

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs

Shiyao Cui, Qinglin Zhang, Xuan Ouyang +6

Toxicity detection in multimodal text-image content faces growing challenges, especially with multimodal implicit toxicity, where each modality appears benign on its own but convey…

cs.CL2025

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models

Cheng Wang, Gelei Deng, Xianglin Yang +2

Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and te…

cs.SE2024

CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision

Hao Wang, Zeyu Gao, Chao Zhang +7

Binary code representation learning has shown significant performance in binary analysis tasks. But existing solutions often have poor transferability, particularly in few-shot and…

cs.CV2021

Privacy-preserving Collaborative Learning with Automatic Transformation Search

Wei Gao, Shangwei Guo, Tianwei Zhang +3

Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their trainin…

cs.CR2026

Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure

Jianshuo Dong, Yiming Liu, Maosen Zhang +6

Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.g., malicious side-tasks hidden in external tool results. While many efforts have sought to address the th…

cs.CL2025

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings

Shujian Yang, Shiyao Cui, Chuanrui Hu +5

Detecting toxic content using language models is important but challenging. While large language models (LLMs) have demonstrated strong performance in understanding Chinese, recent…

cs.CV2025

FaceID-6M: A Large-Scale, Open-Source FaceID Customization Dataset

Shuhe Wang, Xiaoya Li, Jiwei Li +8

Due to the data-driven nature of current face identity (FaceID) customization methods, all state-of-the-art models rely on large-scale datasets containing millions of high-quality…

cs.LG2021

A General Framework for Defending Against Backdoor Attacks via Influence Graph

Xiaofei Sun, Jiwei Li, Xiaoya Li +5

In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attack…