113 citations · 621 across the 55 of their papers we have counts for
57 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…
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
Yue Wang, Yi Liu, Gelei Deng +4
Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a direct distribution channel fo…
Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks
Xiaoyan Feng, Yanjun Zhang, He Zhang +2
Watermarking LLM-generated text is an important task for tracing its provenance. Existing LLM watermarks preserve provenance under editing, but this same robustness allows an adver…
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…
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…
SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents
Yubin Qu, Yi Liu, Gelei Deng +4
A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while the task still completes. We cal…
MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content
Ruoqi Guo, Yi Liu, Gelei Deng +7
Mobile graphical user interface (GUI) agents driven by vision-language models (VLMs) perceive the screen as rendered pixels and choose actions from what they see, so they cannot re…
Rethinking Federated Unlearning via the Lens of Memorization
Jiaheng Wei, Yanjun Zhang, He Zhang +5
Federated learning (FL) increasingly needs machine unlearning to comply with privacy regulations. However, existing federated unlearning approaches may overlook the overlapping inf…
Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
Yubin Qu, Ying Zhang, Yanjun Zhang +4
Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated fil…
How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
Zhihao Chen, Ying Zhang, Yi Liu +7
Large Language Model (LLM) agents increasingly rely on third-party skills that operate within privileged execution environments and routinely handle sensitive credentials, yet how…
"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
Yi Liu, Zhihao Chen, Yanjun Zhang +4
LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privile…
Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
Jun Liu, Leo Yu Zhang, Fengpeng Li +2
Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models. Despite recent progress, existing approaches…
Test-Time Backdoor Detection for Object Detection Models
Hangtao Zhang, Yichen Wang, Shihui Yan +7
Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. De…
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…
ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification
Xianlong Wang, Shengshan Hu, Yechao Zhang +5
Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victi…
Memorization in deep learning: A survey
Jiaheng Wei, Yanjun Zhang, Leo Yu Zhang +5
Deep Learning (DL) powered by Deep Neural Networks (DNNs) has revolutionized various domains, yet understanding the intricacies of DNN decision-making and learning processes remain…
IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
Linshan Hou, Ruili Feng, Zhongyun Hua +3
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model trai…
Large Language Model Watermark Stealing With Mixed Integer Programming
Zhaoxi Zhang, Xiaomei Zhang, Yanjun Zhang +5
The Large Language Model (LLM) watermark is a newly emerging technique that shows promise in addressing concerns surrounding LLM copyright, monitoring AI-generated text, and preven…
Algorithmic Fairness: A Tolerance Perspective
Renqiang Luo, Tao Tang, Feng Xia +5
Recent advancements in machine learning and deep learning have brought algorithmic fairness into sharp focus, illuminating concerns over discriminatory decision making that negativ…
Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
Hangtao Zhang, Shengshan Hu, Yichen Wang +5
Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor a…
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
Ziqi Zhou, Minghui Li, Wei Liu +7
With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trai…
Fluent: Round-efficient Secure Aggregation for Private Federated Learning
Xincheng Li, Jianting Ning, Geong Sen Poh +3
Federated learning (FL) facilitates collaborative training of machine learning models among a large number of clients while safeguarding the privacy of their local datasets. Howeve…
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…
Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
Lulu Xue, Shengshan Hu, Ruizhi Zhao +4
Collaborative learning (CL) is a distributed learning framework that aims to protect user privacy by allowing users to jointly train a model by sharing their gradient updates only.…