activity
20242026
collaborators

22 papers

cs.CV2026

Imperceptible and Reversible Adversarial Examples against Vision-Language Models for Privacy Protection

Qi Lu, Ziqi Zhou, Yufei Song +5

Vision Language Models (VLMs) offer powerful multimodal ability but also expose users to text-based privacy attacks where adversaries crawl online photos and query VLMs to extract…

cs.CY2026

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Hangtao Zhang, Chenyu Zhu, Xianlong Wang +9

Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensi…

cs.CR2026

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics

Hangtao Zhang, Yucheng Zhao, Sishun Liu +8

Jailbreak prompts can bypass alignment guardrails in large language models (LLMs) and elicit unsafe outputs, making reliable deployment-time detection critical. Prior detection app…

cs.LG2026

Towards Reliable Forgetting: A Survey on Machine Unlearning Verification

Lulu Xue, Shengshan Hu, Wei Lu +7

With growing demands for privacy protection, security, and legal compliance (e.g., GDPR), machine unlearning has emerged as a critical technique for ensuring the controllability an…

cs.RO2026

Robot Collapse: Supply Chain Backdoor Attacks Against VLM-based Robotic Manipulation

Xianlong Wang, Hewen Pan, Hangtao Zhang +8

Robotic manipulation policies are increasingly empowered by \textit{large language models} (LLMs) and \textit{vision-language models} (VLMs), leveraging their understanding and per…

cs.CR2026

Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation

Di Mi, Yanjun Zhang, Leo Yu Zhang +4

Model extraction attacks (MEAs) enable an attacker to replicate the functionality of a victim deep neural network (DNN) model by only querying its API service remotely, posing a se…