Related papers: SafeRedirect: Defeating Internal Safety Collapse v…
Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm…
Large Language Models (LLMs) have demonstrated remarkable capabilities in performing tasks across various domains without needing explicit retraining. This capability, known as In-Context Learning (ICL), while impressive, exposes LLMs to a…
With the widespread real-world deployment of large language models (LLMs), ensuring their behavior complies with safety standards has become crucial. Jailbreak attacks exploit vulnerabilities in LLMs to induce undesirable behavior, posing a…
Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…
Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversational safety mechanisms. We introduce Incremental Completion Decomposition (ICD), a…
Large language models (LLMs) are promising tools for supporting security management tasks, such as incident response planning. However, their unreliability and tendency to hallucinate remain significant challenges. In this paper, we address…
Industrial control system (ICS) operations use trusted endpoints like human machine interfaces (HMIs) and workstations to relay commands to programmable logic controllers (PLCs). Because most PLCs lack layered defenses, compromise of a…
Modern code completion engines, powered by large language models (LLMs), assist millions of developers with their strong capabilities to generate functionally correct code. Due to this popularity, it is crucial to investigate the security…
As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…
Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…
In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction…
Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional components. However, existing safety attribution methods…
Large language models (LLMs) for Verilog code generation are increasingly adopted in hardware design, yet remain vulnerable to backdoor attacks where adversaries inject malicious triggers during training to induce vulnerable hardware…
LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination…
In modern software development, multiple software components, often sourced from different contributors, including AI assistants, are combined to create a cohesive system. Although these components might each be individually safe, their…
The security of Industrial Control Systems (ICS) has been attracting increased attention over the past years, following the discovery of real threats targeting industrial environments. Despite this attention, automation of the reverse…
Intellectual Property (IP) theft is a serious concern for the integrated circuit (IC) industry. To address this concern, logic locking countermeasure transforms a logic circuit to a different one to obfuscate its inner details. The…
The application of large language models to code generation has evolved from one-shot generation to iterative refinement, yet the evolution of security throughout iteration remains insufficiently understood. Through comparative experiments…
LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…
LLM-based SOC log classifiers are commonly evaluated using regular-expression pipelines that extract structured fields from free-form model output. We demonstrate that this practice introduces a class of silent, systematic evaluation…