Related papers: Localizing Malicious Outputs from CodeLLM

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key…

Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identifies a vulnerability: LLMs can be manipulated by…

Time series classification (TSC) is a cornerstone of modern web applications, powering tasks such as financial data analysis, network traffic monitoring, and user behavior analysis. In recent years, deep neural networks (DNNs) have greatly…

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

Multimodal Large Language Models (MLLMs) have become powerful and widely adopted in some practical applications. However, recent research has revealed their vulnerability to multimodal jailbreak attacks, whereby the model can be induced to…

Although large language models (LLM) have achieved remarkable performance, their enormous parameter counts hinder deployment on resource-constrained hardware. Low-rank compression can reduce both memory usage and computational demand, but…

Model quantization is critical for deploying large language models (LLMs) on resource-constrained hardware, yet recent work has revealed severe security risks that benign LLMs in full precision may exhibit malicious behaviors after…

The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM's adversarial robustness. This paper proposes an efficient tool to audit the LLM's…

Quantum neural networks (QNNs) are an important model for implementing quantum machine learning (QML), while they demonstrate a high degree of vulnerability to backdoor attacks similar to classical networks. To address this issue, a quantum…

Though safety alignment has been applied to most large language models (LLMs), LLM service providers generally deploy a subsequent moderation as the external safety guardrail in real-world products. Existing moderators mainly practice a…

Large language models (LLMs) introduce new security risks, but there are few comprehensive evaluation suites to measure and reduce these risks. We present BenchmarkName, a novel benchmark to quantify LLM security risks and capabilities. We…

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…

While neural ranking models (NRMs) have shown high effectiveness, they remain susceptible to adversarial manipulation. In this work, we introduce Few-Shot Adversarial Prompting (FSAP), a novel black-box attack framework that leverages the…

This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand the text from left to right and find that they struggle to…

Mainstream backdoor attacks on large language models (LLMs) typically set a fixed trigger in the input instance and specific responses for triggered queries. However, the fixed trigger setting (e.g., unusual words) may be easily detected by…

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Deep learning malware detectors achieve high classification accuracy but suffer from severe interpretability limitations, typically returning probabilistic verdicts that lack forensic context. We introduce AsmRAG, a framework performing…

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

The rapid evolution of malware variants requires robust classification methods to enhance cybersecurity. While Large Language Models (LLMs) offer potential for generating malware descriptions to aid family classification, their utility is…