36 citations · 40 across the 48 of their papers we have counts for
18 papers · 1 filter
SteerProbe: Learning to Bypass Safety Steering in Vision-Language Models
Xinwei Zhang, Aoting Hu, Hangcheng Liu +3
Activation steering offers an inference-time defense for vision--language models (VLMs) by modifying intermediate representations without updating backbone parameters. However, pro…
DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections
Li Hu, Kanghua Mo, Yingbin Jin +2
As GUI-based mobile agents rapidly progress, rigorous safety evaluation of their autonomous decision-making in realistic app interfaces becomes increasingly critical. Existing benc…
SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents
Xiaoyu Xu, Zi Liang, Minxin Du +4
Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effects that t…
FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models
Haoyang Li, Ruoxi Sun, Qingqing Ye +4
Text-to-image diffusion models enable data-efficient "mimicry" attacks, wherein adversaries fine-tune the model on a handful of public photos to synthesize convincing forgeries of…
Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions
Xiaoyu Xu, Minxin Du, Li Bai +8
Machine unlearning aims to remove target influence while preserving other capabilities. This survey compares methods, benchmarks, and evidence across large language models and syst…
CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?
Zi Liang, Xiaoyu Xu, Yanyun Wang +3
Prompt injection attacks on Large Language Model (LLM) agents seek to introduce malicious instructions or content into external text sources retrieved by agents, forcing the underl…
Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure
Zi Liang, Ronghua Li, Yanyun Wang +2
Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastruc…
When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
Xiaoyu Xu, Minxin Du, Qipeng Xie +3
Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability…
Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
Yanyun Wang, Qingqing Ye, Li Liu +2
Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and a…
IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-off
Linyan Dai, Xinwei Zhang, Haoyang Li +2
Personalized text-to-image diffusion models (e.g., DreamBooth, LoRA) enable users to synthesize high-fidelity avatars from a few reference photos for social expression. However, on…
Robust Single-message Shuffle Differential Privacy Protocol for Accurate Distribution Estimation
Xiaoguang Li, Hanyi Wang, Yaowei Huang +6
Shuffler-based differential privacy (shuffle-DP) is a privacy paradigm providing high utility by involving a shuffler to permute noisy report from users. Existing shuffle-DP protoc…
Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models
Xinwei Zhang, Li Bai, Tianwei Zhang +5
Large vision-language models (LVLMs) have achieved impressive performance across multimodal tasks, but their reliance on visual inputs exposes them to adversarial threats. Encoder-…
Machine Unlearning in Low-Dimensional Feature Subspace
Kun Fang, Qinghua Tao, Junxu Liu +5
Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspectiv…
United We Defend: Collaborative Membership Inference Defenses in Federated Learning
Li Bai, Junxu Liu, Sen Zhang +3
Membership inference attacks (MIAs), which determine whether a specific data point was included in the training set of a target model, have posed severe threats in federated learni…
FIT to Forget: Robust Continual Unlearning for Large Language Models
Xiaoyu Xu, Minxin Du, Kun Fang +5
While large language models (LLMs) exhibit remarkable capabilities, they increasingly face demands to unlearn memorized privacy-sensitive, copyrighted, or harmful content. Existing…
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
Xinwei Zhang, Hangcheng Liu, Li Bai +4
Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. W…
When Backdoors Meet Partial Observability: Attacking Real-World Reinforcement Learning
Tairan Huang, Qingqing Ye, Yulin Jin +4
Backdoor attacks can cause reinforcement learning (RL) policies to behave normally under clean inputs while executing malicious behaviors when triggers are present. Existing RL bac…
From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
Xiaoyu Xu, Minxin Du, Zitong Li +6
Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfully represent the true ``forgettin…