21 papers
Beyond the Prompt: Recovering Hidden Concepts in Text-to-Image Models
Zhengfeng Zheng, Minghong Fang
Text-to-image models can generate visual concepts that their prompts never mention, and recent work shows that such associations can be implanted so that ordinary prompts trigger t…
Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning
Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu +2
Fine-tuning-as-a-service lets users adapt a safety-aligned language model to their own data, but it also creates a harmful fine-tuning attack surface: a small amount of harmful dat…
Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue
Omar Sheta, Rinku Deuja, Hadi Masoudi +1
Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns instead of a single prompt. Gra…
RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation
Yueyang Quan, Anjun Gao, Yufei Xia +2
Retrieval-augmented generation (RAG) improves the factuality of large language models by grounding responses in external documents, but it also exposes a critical security vulnerab…
NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
Anjun Gao, Yueyang Quan, Yufei Xia +2
Safety alignment in large language models (LLMs) remains brittle against a growing spectrum of attacks. Jailbreak attacks bypass safety mechanisms through crafted prompts, while ne…
Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions
Anjun Gao, Yueyang Quan, Zhuqing Liu +1
Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these models remain vulnerable to backdo…
Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems
Yufei Xia, Anjun Gao, Yueyang Quan +2
Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new ch…
Patcher: Post-Hoc Patching of Backdoored Large Language Models
Anjun Gao, Yueyang Quan, Yufei Xia +2
Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms. Existi…
Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment
Nguyen Linh Bao Nguyen, Wanlun Ma, Viet Vo +4
Retrieval-augmented generation (RAG) has become central to large language model (LLM) deployments, grounding responses in enterprise or proprietary data to reduce hallucinations. H…
SecureAFL: Secure Asynchronous Federated Learning
Anjun Gao, Feng Wang, Zhenglin Wan +3
Federated learning (FL) enables multiple clients to collaboratively train a global machine learning model via a server without sharing their private training data. In traditional F…
SecureSplit: Mitigating Backdoor Attacks in Split Learning
Zhihao Dou, Dongfei Cui, Weida Wang +7
Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct fea…
When the Server Steps In: Calibrated Updates for Fair Federated Learning
Tianrun Yu, Kaixiang Zhao, Cheng Zhang +4
Federated learning (FL) has emerged as a transformative distributed learning paradigm, enabling multiple clients to collaboratively train a global model under the coordination of a…
Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
Baolei Zhang, Minghong Fang, Zhuqing Liu +5
Federated Learning (FL) allows multiple clients to collaboratively train a model without sharing their private data. However, FL is vulnerable to Byzantine attacks, where adversari…
Secure Retrieval-Augmented Generation against Poisoning Attacks
Zirui Cheng, Jikai Sun, Anjun Gao +4
Large language models (LLMs) have transformed natural language processing (NLP), enabling applications from content generation to decision support. Retrieval-Augmented Generation (…
Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
Baolei Zhang, Haoran Xin, Yuxi Chen +6
Retrieval-Augmented Generation (RAG) integrates external knowledge into large language models to improve response quality. However, recent work has shown that RAG systems are highl…
Fairness-Constrained Optimization Attack in Federated Learning
Harsh Kasyap, Minghong Fang, Zhuqing Liu +2
Federated learning (FL) is a privacy-preserving machine learning technique that facilitates collaboration among participants across demographics. FL enables model sharing, while re…
Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approach
Yueyang Quan, Chang Wang, Shengjie Zhai +2
Decentralized min-max optimization allows multi-agent systems to collaboratively solve global min-max optimization problems by facilitating the exchange of model updates among neig…
Benchmarking Poisoning Attacks against Retrieval-Augmented Generation
Baolei Zhang, Haoran Xin, Jiatong Li +5
Retrieval-Augmented Generation (RAG) has proven effective in mitigating hallucinations in large language models by incorporating external knowledge during inference. However, this…
Toward Malicious Clients Detection in Federated Learning
Zhihao Dou, Jiaqi Wang, Wei Sun +2
Federated learning (FL) enables multiple clients to collaboratively train a global machine learning model without sharing their raw data. However, the decentralized nature of FL in…
Traceback of Poisoning Attacks to Retrieval-Augmented Generation
Baolei Zhang, Haoran Xin, Minghong Fang +4
Large language models (LLMs) integrated with retrieval-augmented generation (RAG) systems improve accuracy by leveraging external knowledge sources. However, recent research has re…
Practical Poisoning Attacks against Retrieval-Augmented Generation
Baolei Zhang, Yuxi Chen, Zhuqing Liu +4
Large language models (LLMs) have demonstrated impressive natural language processing abilities but face challenges such as hallucination and outdated knowledge. Retrieval-Augmente…