4 citations · 17 across the 34 of their papers we have counts for
18 papers · 1 filter
Review of Hallucination Understanding in Large Language and Vision Models
Zhengyi Ho, Siyuan Liang, Dacheng Tao
The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrec…
Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
Yisong Xiao, Aishan Liu, Siyuan Liang +3
Large Language Models (LLMs) have demonstrated impressive performance across various tasks, yet they remain vulnerable to generating toxic content, necessitating detoxification str…
MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving
Aishan Liu, Jiakai Wang, Tianyuan Zhang +6
Evaluating and ensuring the adversarial robustness of autonomous driving (AD) systems is a critical and unresolved challenge. This paper introduces MetAdv, a novel adversarial test…
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
Zonghao Ying, Siyang Wu, Run Hao +44
Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks…
ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
Zhiyao Ren, Siyuan Liang, Aishan Liu +1
In-context learning (ICL) has demonstrated remarkable success in large language models (LLMs) due to its adaptability and parameter-free nature. However, it also introduces a criti…
T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
Jiayang Liu, Siyuan Liang, Shiqian Zhao +5
In recent years, fueled by the rapid advancement of diffusion models, text-to-video (T2V) generation models have achieved remarkable progress, with notable examples including Pika,…
AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
Zonghao Ying, Le Wang, Yisong Xiao +7
The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands,…
ME: Trigger Element Combination Backdoor Attack on Copyright Infringement
Feiyu Yang, Siyuan Liang, Aishan Liu +1
The capability of generative diffusion models (DMs) like Stable Diffusion (SD) in replicating training data could be taken advantage of by attackers to launch the Copyright Infring…
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
Shuhan Xu, Siyuan Liang, Hongling Zheng +6
Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject…
T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models
Siyuan Liang, Jiayang Liu, Jiecheng Zhai +5
The rapid development of generative artificial intelligence has made text to video models essential for building future multimodal world simulators. However, these models remain vu…
Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models
Yisong Xiao, Aishan Liu, Siyuan Liang +2
LLMs have demonstrated remarkable performance across diverse applications, yet they inadvertently absorb spurious correlations from training data, leading to stereotype association…
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…
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Junyu Luo, Weizhi Zhang, Ye Yuan +23
The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic a…
Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
Zonghao Ying, Guangyi Zheng, Yongxin Huang +6
This study presents the first comprehensive safety evaluation of the DeepSeek models, focusing on evaluating the safety risks associated with their generated content. Our evaluatio…
Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
Zonghao Ying, Deyue Zhang, Zonglei Jing +7
Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. Howev…
ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models
Xuxu Liu, Siyuan Liang, Mengya Han +5
Generative large language models are crucial in natural language processing, but they are vulnerable to backdoor attacks, where subtle triggers compromise their behavior. Although…
Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving
Lu Wang, Tianyuan Zhang, Yang Qu +5
Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities; however, these models remain highly susceptible to adversaria…
CogMorph: Cognitive Morphing Attacks for Text-to-Image Models
Zonglei Jing, Zonghao Ying, Le Wang +4
The development of text-to-image (T2I) generative models, that enable the creation of high-quality synthetic images from textual prompts, has opened new frontiers in creative desig…