相关论文: Localizing Malicious Outputs from CodeLLM

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective…

The rapid advancement of large language models (LLMs) has brought significant benefits to various domains while introducing substantial risks. Despite being fine-tuned through reinforcement learning, LLMs lack the capability to discern…

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:…

Despite the notable success of language models (LMs) in various natural language processing (NLP) tasks, the reliability of LMs is susceptible to backdoor attacks. Prior research attempts to mitigate backdoor learning while training the LMs…

The integration of large language models (LLMs) into information retrieval systems introduces new attack surfaces, particularly for adversarial ranking manipulations. We present $\textbf{StealthRank}$, a novel adversarial attack method that…

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction…

The increasing use of Large Language Models (LLMs) for generating highly coherent and contextually relevant text introduces new risks, including misuse for unethical purposes such as disinformation or academic dishonesty. To address these…

The fusion of Large Language Models (LLMs) with recommender systems (RecSys) has dramatically advanced personalized recommendations and drawn extensive attention. Despite the impressive progress, the safety of LLM-based RecSys against…

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…

Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing…

While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM input space is discrete, which precludes gradient-based…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasibility of backdoor attacks against LLMs. However, existing…

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to…

Jailbreaking large-language models (LLMs) involves testing their robustness against adversarial prompts and evaluating their ability to withstand prompt attacks that could elicit unauthorized or malicious responses. In this paper, we…

Security research is fundamentally a problem of resource constraint and consequent prioritization. There is simply too much attack surface and too little time and energy to spend analyzing it all. The most effective security researchers are…

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the…

With the growing adoption of reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs), the risk of backdoor installation during alignment has increased, leading to unintended and harmful behaviors.…

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…