5 citations · 13 across the 20 of their papers we have counts for
22 papers
JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization
Haolun Zheng, Yu He, Tailun Chen +6
Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed…
AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
Yu He, Haozhe Zhu, Yiming Li +4
LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defen…
MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
Tailun Chen, Yu He, Yan Wang +9
Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While recent studies have demonstrated…
Black-Box Guardrail Reverse-engineering Attack
Hongwei Yao, Yun Xia, Shuo Shao +3
Large language models (LLMs) increasingly employ guardrails to enforce ethical, legal, and application-specific constraints on their outputs. While effective at mitigating harmful…
Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis
Yiling He, Junchi Lei, Hongyu She +5
Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat landscapes evolve…
External Data Extraction Attacks against Retrieval-Augmented Large Language Models
Yu He, Yifei Chen, Yiming Li +5
In recent years, RAG has emerged as a key paradigm for enhancing large language models (LLMs). By integrating externally retrieved information, RAG alleviates issues like outdated…
PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs
Yuchen Yang, Yiming Li, Hongwei Yao +6
System prompts are critical for shaping the behavior and output quality of large language model (LLM)-based applications, driving substantial investment in optimizing high-quality…
MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
Weiwei Qi, Shuo Shao, Wei Gu +4
Large Language Models (LLMs) have exhibited remarkable capabilities but remain vulnerable to jailbreaking attacks, which can elicit harmful content from the models by manipulating…
Quantifying Conversation Drift in MCP via Latent Polytope
Haoran Shi, Hongwei Yao, Shuo Shao +4
The Model Context Protocol (MCP) enhances large language models (LLMs) by integrating external tools, enabling dynamic aggregation of real-time data to improve task execution. Howe…
SoK: Large Language Model Copyright Auditing via Fingerprinting
Shuo Shao, Yiming Li, Yu He +4
The broad capabilities and substantial resources required to train Large Language Models (LLMs) make them valuable intellectual property, yet they remain vulnerable to copyright in…
Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
Zhifan Luo, Shuo Shao, Su Zhang +5
The Key-Value (KV) cache, which stores intermediate attention computations (Key and Value pairs) to avoid redundant calculations, is a fundamental mechanism for accelerating Large…
DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective
Shuo Shao, Yiming Li, Mengren Zheng +7
The widespread application of Deep Learning across diverse domains hinges critically on the quality and composition of training datasets. However, the common lack of disclosure reg…
Rethinking Data Protection in the (Generative) Artificial Intelligence Era
Yiming Li, Shuo Shao, Yu He +8
The (generative) artificial intelligence (AI) era has profoundly reshaped the meaning and value of data. No longer confined to static content, data now permeates every stage of the…
SmartGuard: Leveraging Large Language Models for Network Attack Detection through Audit Log Analysis and Summarization
Hao Zhang, Shuo Shao, Song Li +3
End-point monitoring solutions are widely deployed in today's enterprise environments to support advanced attack detection and investigation. These monitors continuously record sys…
CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
Yiming Li, Kaiying Yan, Shuo Shao +5
Speaker verification models are trained on large-scale public datasets whose licenses usually prohibit unauthorized commercial use, yet such infringement is difficult to detect or…
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
Yukun Chen, Shuo Shao, Enhao Huang +4
Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training…
FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint
Shuo Shao, Haozhe Zhu, Yiming Li +3
Model fingerprinting has emerged as a crucial mechanism for safeguarding the intellectual property of open-source models, offering a non-intrusive approach that requires no modific…
SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI
Kui Ren, Ziqi Yang, Li Lu +6
The rapid advancement of AI technology, particularly in generating AI-generated content (AIGC), has transformed numerous fields, e.g., art video generation, but also brings new ris…
PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark
Cheng Wei, Yang Wang, Kuofeng Gao +4
Recently, point clouds have been widely used in computer vision, whereas their collection is time-consuming and expensive. As such, point cloud datasets are the valuable intellectu…
Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
Shuo Shao, Yiming Li, Hongwei Yao +3
Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a giv…
FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model
Shuo Shao, Wenyuan Yang, Hanlin Gu +4
Federated learning (FL) is a distributed machine learning paradigm allowing multiple clients to collaboratively train a global model without sharing their local data. However, FL e…
Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooring
Wenyuan Yang, Shuo Shao, Yue Yang +5
Federated learning (FL) allows multiple participants to collaboratively build deep learning (DL) models without directly sharing data. Consequently, the issue of copyright protecti…