10 citations · 17 across the 18 of their papers we have counts for
18 papers
ARENA: Automated Red-Teaming for Large Audio Language Models
Jiaming He, Zhicong Huang, Tian Jin +5
Large audio-language models (LALMs) make it possible to interact with language models through speech, music, and environmental sound, but they also introduce a safety surface that…
PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation
Leyi Sheng, Han Sun, Zhen Sun +4
As Text-to-Image (T2I) jailbreak techniques evolve rapidly, existing benchmarks and reproduction workflows often struggle to keep pace. More importantly, T2I jailbreak evaluation i…
Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition
Yifan Liao, Zongmin Zhang, Zhen Sun +3
Automatic speech recognition (ASR) systems have become widely used for multilingual speech-to-text transcription. Their robustness to adversarial attacks has become an important to…
When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer
Zhen Sun, Yifan Liao, Zhicong Huang +4
Machine-generated text (MGT) attribution aims to identify the specific generator responsible for a given text, thereby providing fine-grained evidence for model accountability and…
On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models
Yule Liu, Yilong Yang, Jiale Teng +11
Recent advances in image-to-3D models have significantly improved the fidelity and accessibility of 3D content creation. Such a powerful reconstruction capability that enables crea…
IPV-Bench: Benchmarking Image Protection Methods under Diverse Image-to-Video Generation Scenarios
Xiaofeng Li, Leyi Sheng, Yifan Zhao +4
Image-to-video (I2V) generation models can be misused to animate a single image into a convincing fake video, motivating perturbation-based image protection methods that aim to dis…
6DAttack: Backdoor Attacks in the 6DoF Pose Estimation
Jihui Guo, Zongmin Zhang, Zhen Sun +4
Deep learning advances have enabled accurate six-degree-of-freedom (6DoF) object pose estimation, widely used in robotics, AR/VR, and autonomous systems. However, backdoor attacks…
Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models
Zongmin Zhang, Zhen Sun, Yifan Liao +5
Prompt-driven Video Segmentation Foundation Models (VSFMs), such as SAM2, are increasingly used in applications including autonomous driving and digital pathology, yet their securi…
"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios
Zhen Sun, Zongmin Zhang, Deqi Liang +8
As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-cr…
Work Zones challenge VLM Trajectory Planning: Toward Mitigation and Robust Autonomous Driving
Yifan Liao, Zhen Sun, Xiaoyun Qiu +7
Visual Language Models (VLMs), with powerful multimodal reasoning capabilities, are gradually integrated into autonomous driving by several automobile manufacturers to enhance plan…
Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
Zhiyuan Zhong, Zhen Sun, Yepang Liu +2
Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden…
SynDec: A Synthesize-then-Decode Approach for Arbitrary Textual Style Transfer via Large Language Models
Han Sun, Zhen Sun, Zongmin Zhang +3
Large Language Models (LLMs) are emerging as dominant forces for textual style transfer. However, for arbitrary style transfer, LLMs face two key challenges: (1) considerable relia…
Can VLMs Detect and Localize Fine-Grained AI-Edited Images?
Zhen Sun, Ziyi Zhang, Zeren Luo +10
Fine-grained detection and localization of localized image edits is crucial for assessing content authenticity, especially as modern diffusion models and image editors can produce…
"I Can See Forever!": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments
Ziyi Zhang, Zhen Sun, Zongmin Zhang +6
The visually impaired population faces significant challenges in daily activities. While prior works employ vision language models for assistance, most focus on static content and…
FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts
Ziyi Zhang, Zhen Sun, Zongmin Zhang +2
Multimodal Large Language Models (MLLMs) have become powerful and widely adopted in some practical applications. However, recent research has revealed their vulnerability to multim…
Quantized Delta Weight Is Safety Keeper
Yule Liu, Zhen Sun, Xinlei He +1
Recent advancements in fine-tuning proprietary language models enable customized applications across various domains but also introduce two major challenges: high resource demands…
PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning
Zhen Sun, Tianshuo Cong, Yule Liu +5
Fine-tuning is an essential process to improve the performance of Large Language Models (LLMs) in specific domains, with Parameter-Efficient Fine-Tuning (PEFT) gaining popularity d…
Jailbreak Attacks and Defenses Against Large Language Models: A Survey
Sibo Yi, Yule Liu, Zhen Sun +5
Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assis…