2 citations · 7 across the 35 of their papers we have counts for
38 papers
Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation
Ziqi Zhou, Yifan Hu, Yufei Song +5
The Segment Anything Model (SAM) achieves remarkable performance in visual segmentation. The latest SAM3 extends promptable segmentation to concept-level prediction, broadening the…
UBA-ORL: Unlearning-Activated Backdoor Attacks on Offline Reinforcement Learning
Fengyi Wang, Cong Li, Lulu Xue +3
Offline reinforcement learning (offline RL) enables policy learning from pre-collected static datasets without online exploration, and is increasingly deployed not only in safety-c…
SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL
Kai Ruan, Jinghao Lin, Qianshan Wei +2
Group-relative reinforcement learning waits for sibling rollouts of the same prompt, which is costly for long and variable tool-use trajectories. Single-stream Policy Optimization…
Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification
Yutong Wu, Xiaofan Bai, Shixin Li +10
Large language models (LLMs) are high-value assets that can be derived through redeployment, fine-tuning, quantization, or further alignment. Because deployed LLMs are commonly exp…
When Does Muon Help Agentic Reinforcement Learning?
Kai Ruan, Jinghao Lin, Zihe Huang +4
Muon is competitive with AdamW in large-scale pre-training, but its operating regime in reinforcement-learning post-training remains unclear. We map this regime on ALFWorld, a spar…
TYPO: Instruction-Dense Visual Jailbreaks against Commercial Closed-Source Image-Generation Models
Meng Xie, Li Zeng, Hangtao Zhang +4
Recent commercial image-generation models can generate high-quality images with readable text (e.g., posters, infographics, and manuals), attracting considerable attention. Yet we…
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
Kai Ruan, Zihe Huang, Ziqi Zhou +4
Large language model (LLM) agents often waste inference compute by continuing multi-step trajectories that are already doomed to fail. We study early failure prediction and inferen…
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…
Dual-branch Robust Unlearnable Examples
Xianlong Wang, Hangtao Zhang, Wenbo Pan +4
Unlearnable examples (UEs) aim to compromise model training by injecting imperceptible perturbations to clean samples. However, existing UE schemes exhibit limited robustness again…
PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation
Yuhang Huang, Xuan Lv, Junyan Xu +25
World foundation models (WFMs) are powerful simulators, yet they predominantly operate in a single-view setting and lack the multi-view 3D consistency required for robotic manipula…
VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasion
Shihui Yan, Hu Liu, Junyu Shi +6
Adversarial camouflage in the physical world remains highly challenging, particularly under UAV reconnaissance where targets undergo continuous geometric changes and extreme illumi…
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…
Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving
Zihui Zhu, Ziqi Zhou, Yichen Wang +3
Deep learning drives major advances in autonomous driving (AD), where object detectors are central to perception. However, adversarial attacks pose significant threats to the relia…
Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models
Shihui Yan, Ziqi Zhou, Yufei Song +3
Physical adversarial patch attacks critically threaten pedestrian detection, causing surveillance and autonomous driving systems to miss pedestrians and creating severe safety risk…
UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
Lulu Xue, Shengshan Hu, Wei Lu +6
Machine unlearning is an emerging technique that aims to remove the influence of specific data from trained models, thereby enhancing privacy protection. However, recent research h…
Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustness
Yufei Song, Ziqi Zhou, Menghao Deng +4
Existing segmentation models exhibit significant vulnerability to adversarial attacks.To improve robustness, adversarial training incorporates adversarial examples into model train…
UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
Hewen Pan, Cong Wei, Dashuang Liang +8
With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existi…
Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2
Ziqi Zhou, Yifan Hu, Yufei Song +6
Recent studies reveal the vulnerability of the image segmentation foundation model SAM to adversarial examples. Its successor, SAM2, has attracted significant attention due to its…
SegTrans: Transferable Adversarial Examples for Segmentation Models
Yufei Song, Ziqi Zhou, Qi Lu +6
Segmentation models exhibit significant vulnerability to adversarial examples in white-box settings, but existing adversarial attack methods often show poor transferability across…
DarkHash: A Data-Free Backdoor Attack Against Deep Hashing
Ziqi Zhou, Menghao Deng, Yufei Song +6
Benefiting from its superior feature learning capabilities and efficiency, deep hashing has achieved remarkable success in large-scale image retrieval. Recent studies have demonstr…
Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Faces
Junyu Shi, Minghui Li, Junguo Zuo +8
Deepfakes, leveraging advanced AIGC (Artificial Intelligence-Generated Content) techniques, create hyper-realistic synthetic images and videos of human faces, posing a significant…
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
Wei Wan, Yuxuan Ning, Zhicong Huang +7
Federated Learning (FL) is a distributed paradigm aimed at protecting participant data privacy by exchanging model parameters to achieve high-quality model training. However, this…
ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
Yichen Wang, Hangtao Zhang, Hewen Pan +7
Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous…
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…