36 citations · 40 across the 48 of their papers we have counts for
31 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 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-…
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…
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…
Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks
Yaxin Xiao, Qingqing Ye, Zi Liang +4
Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through…
Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
Zi Liang, Qingqing Ye, Xuan Liu +3
Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance of large language models (LLMs) during trainin…
Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
Li Bai, Qingqing Ye, Xinwei Zhang +4
Machine learning models are often vulnerable to inference attacks that expose sensitive information from their training data. Shadow model technique is commonly employed in such at…
MER-Inspector: Assessing model extraction risks from an attack-agnostic perspective
Xinwei Zhang, Haibo Hu, Qingqing Ye +2
Information leakage issues in machine learning-based Web applications have attracted increasing attention. While the risk of data privacy leakage has been rigorously analyzed, the…
WiFinger: Fingerprinting Noisy IoT Event Traffic Using Packet-level Sequence Matching
Ronghua Li, Shinan Liu, Haibo Hu +2
IoT environments such as smart homes are susceptible to privacy inference attacks, where attackers can analyze patterns of encrypted network traffic to infer the state of devices a…
Dual Utilization of Perturbation for Stream Data Publication under Local Differential Privacy
Rong Du, Qingqing Ye, Yaxin Xiao +3
Stream data from real-time distributed systems such as IoT, tele-health, and crowdsourcing has become an important data source. However, the collection and analysis of user-generat…
Multi-class Item Mining under Local Differential Privacy
Yulian Mao, Qingqing Ye, Rong Du +3
Item mining, a fundamental task for collecting statistical data from users, has raised increasing privacy concerns. To address these concerns, local differential privacy (LDP) was…
Privacy for Free: Leveraging Local Differential Privacy Perturbed Data from Multiple Services
Rong Du, Qingqing Ye, Yue Fu +1
Local Differential Privacy (LDP) has emerged as a widely adopted privacy-preserving technique in modern data analytics, enabling users to share statistical insights while maintaini…
Federated Heavy Hitter Analytics with Local Differential Privacy
Yuemin Zhang, Qingqing Ye, Haibo Hu
Federated heavy hitter analytics enables service providers to better understand the preferences of cross-party users by analyzing the most frequent items. As with federated learnin…
Data Poisoning Attacks to Local Differential Privacy Protocols for Graphs
Xi He, Kai Huang, Qingqing Ye +1
Graph analysis has become increasingly popular with the prevalence of big data and machine learning. Traditional graph data analysis methods often assume the existence of a trusted…
Membership Inference Attacks and Defenses in Federated Learning: A Survey
Li Bai, Haibo Hu, Qingqing Ye +3
Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devi…
"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation
Zi Liang, Qingqing Ye, Yanyun Wang +5
Model extraction attacks (MEAs) on large language models (LLMs) have received increasing attention in recent research. However, existing attack methods typically adapt the extracti…