相关论文: Jailbreaking is (Mostly) Simpler Than You Think

Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks,…

Application Programming Interface (API) Injection attacks refer to the unauthorized or malicious use of APIs, which are often exploited to gain access to sensitive data or manipulate online systems for illicit purposes. Identifying actors…

Visual language modeling for automated driving is emerging as a promising research direction with substantial improvements in multimodal reasoning capabilities. Despite its advanced reasoning abilities, VLM-AD remains vulnerable to serious…

Evaluating the correctness of code generated by AI is a challenging open problem. In this paper, we propose a fully automated method, named ACCA, to evaluate the correctness of AI-generated code for security purposes. The method uses…

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit…

Industrial control systems (ICS), which in many cases are components of critical national infrastructure, are increasingly being connected to other networks and the wider internet motivated by factors such as enhanced operational…

Adversarial attacks perturb images such that a deep neural network produces incorrect classification results. A promising approach to defend against adversarial attacks on natural multi-object scenes is to impose a context-consistency…

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

Large Language Model (LLM) agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function…

Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing approaches break under exploration complexity and intent drift. We propose SEMA, a simple yet…

AI agents integrated with Web3 offer autonomy and openness but raise security concerns as they interact with financial protocols and immutable smart contracts. This paper investigates the vulnerabilities of AI agents within blockchain-based…

As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures…

We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural networks. In contrast to adversarial data modification,…

Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…

Autonomous AI agents executing multi-step tool sequences face semantic attacks that manifest in behavioral traces rather than isolated prompts. A critical challenge is cross-attack generalization: can detectors trained on known attack…

In the era of rapid generative AI development, interactions with large language models (LLMs) pose increasing risks of misuse. Prior research has primarily focused on attacks using template-based prompts and optimization-oriented methods,…

As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms designed to filter malicious queries while being easy to implement and update. In this…

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…

Safety cases, structured arguments that a system is acceptably safe, are becoming central to the governance of AI systems. Yet, traditional safety-case practices from aviation or nuclear engineering rely on well-specified system boundaries,…