30 citations · 133 across the 49 of their papers we have counts for
52 papers
TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling
Ling Zhou, Yihao Huang, Jingling Sun +4
Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and image-based jailbreaks, video ja…
QuISE: Defense against Typographic Attacks on VLMs via Query-Irrelevant Semantic Editing
Shubin Lu, Jiaqi Yin, Yihao Huang
Typographic attacks pose a critical threat to vision-language models (VLMs) by injecting misleading text into images and causing models to rely on adversarial textual cues rather t…
ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization
Hujian Zhu, Yihao Huang, Felix Juefei-Xu +5
Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift jailbreaks have recently em…
Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models
Dongdong An, Pengjie Zhao, Yihao Huang +5
Recent Vision-Language-Action (VLA) models achieve promising performance in robotic manipulation, typically measured by success rates aggregated over predefined object configuratio…
Clarity Is Not Assumed: Understanding LLM-Based Code Generation under Ambiguous Requirements
Di Yang, Xinou Xie, Xiuwen Yang +7
Software requirement ambiguity is ubiquitous in real-world development, stemming from the inherent imprecision of natural language and the varying interpretations of stakeholders.…
Verify Claimed Text-to-Image Models via Boundary-Aware Prompt Optimization
Zidong Zhao, Yihao Huang, Qing Guo +5
As Text-to-Image (T2I) generation becomes widespread, third-party platforms increasingly integrate multiple model APIs for convenient image creation. However, false claims of using…
OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
Xiaojun Jia, Jie Liao, Qi Guo +11
Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks…
Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack
Chenyang Li, Wenbing Tang, Yihao Huang +4
Vision-and-Language Navigation (VLN) agents have made remarkable progress, but their robustness remains insufficiently studied. Existing adversarial evaluations often rely on pertu…
Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection
Jiayi Zhu, Yihao Huang, Yue Cao +5
Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to u…
Seeing It Before It Happens: In-Generation NSFW Detection for Diffusion-Based Text-to-Image Models
Fan Yang, Yihao Huang, Jiayi Zhu +4
Diffusion-based text-to-image (T2I) models enable high-quality image generation but also pose significant risks of misuse, particularly in producing not-safe-for-work (NSFW) conten…
Time-variant Image Inpainting via Interactive Distribution Transition Estimation
Yun Xing, Qing Guo, Xiaoguang Li +5
In this work, we focus on a novel and practical task, i.e., Time-vAriant iMage inPainting (TAMP). The aim of TAMP is to restore a damaged target image by leveraging the complementa…
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Xiaojun Jia, Sensen Gao, Simeng Qin +7
Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples. While existing methods typically achieve targeted attacks by aligning global featur…
PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage
Wenyi Zhang, Ju Jia, Xiaojun Jia +4
The multimodal datasets can be leveraged to pre-train large-scale vision-language models by providing cross-modal semantics. Current endeavors for determining the usage of datasets…
A Vision for Auto Research with LLM Agents
Chengwei Liu, Chong Wang, Jiayue Cao +16
This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Levera…
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…
Privacy Protection Against Personalized Text-to-Image Synthesis via Cross-image Consistency Constraints
Guanyu Wang, Kailong Wang, Yihao Huang +3
The rapid advancement of diffusion models and personalization techniques has made it possible to recreate individual portraits from just a few publicly available images. While such…
Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models
Xiaojun Jia, Sensen Gao, Simeng Qin +6
Large pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive generalization but remain highly vulnerable to adversarial examples (AEs). Previous work has e…
Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution
Yihao Huang, Xin Luo, Qing Guo +5
The advent of local continuous image function (LIIF) has garnered significant attention for arbitrary-scale super-resolution (SR) techniques. However, while the vulnerabilities of…
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
Lingzhi Yuan, Xinfeng Li, Chejian Xu +6
Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, pa…
Concept Guided Co-salient Object Detection
Jiayi Zhu, Qing Guo, Felix Juefei-Xu +3
Co-salient object detection (Co-SOD) aims to identify common salient objects across a group of related images. While recent methods have made notable progress, they typically rely…
What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA
Zhiyuan Chang, Mingyang Li, Xiaojun Jia +5
Incorporating external knowledge has emerged as a promising way to mitigate outdated knowledge and hallucinations in LLM. However, external knowledge is often imperfect, encompassi…
Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
Ma Teng, Jia Xiaojun, Duan Ranjie +5
With the rapid advancement of multimodal large language models (MLLMs), concerns regarding their security have increasingly captured the attention of both academia and industry. Al…
Global Challenge for Safe and Secure LLMs Track 1
Xiaojun Jia, Yihao Huang, Yang Liu +27
This paper introduces the Global Challenge for Safe and Secure Large Language Models (LLMs), a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme…
Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
Xiaojun Jia, Sensen Gao, Qing Guo +6
Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of tra…