相关论文: BadJudge: Backdoor Vulnerabilities of LLM-as-a-Jud…

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems. Despite these critical applications, no existing work has analyzed the vulnerability of…

Large Language Models (LLMs) are increasingly employed as evaluators (LLM-as-a-Judge) for assessing the quality of machine-generated text. This paradigm offers scalability and cost-effectiveness compared to human annotation. However, the…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt model updates. This paper challenges this paradigm by investigating a more pervasive and…

Recent advances in federated learning have demonstrated its promising capability to learn on decentralized datasets. However, a considerable amount of work has raised concerns due to the potential risks of adversaries participating in the…

Large amounts of incremental learning algorithms have been proposed to alleviate the catastrophic forgetting issue arises while dealing with sequential data on a time series. However, the adversarial robustness of incremental learners has…

Knowledge poisoning poses a critical threat to Retrieval-Augmented Generation (RAG) systems by injecting adversarial content into knowledge bases, tricking Large Language Models (LLMs) into producing attacker-controlled outputs grounded in…

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

LLM as judge systems used to assess text quality code correctness and argument strength are vulnerable to prompt injection attacks. We introduce a framework that separates content author attacks from system prompt attacks and evaluate five…

Code LLMs are increasingly employed in software development. However, studies have shown that they are vulnerable to backdoor attacks: when a trigger (a specific input pattern) appears in the input, the backdoor will be activated and cause…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been…

Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to…