Related papers: Refusal Evaluation in Coding LLMs and Code Agents:…

[Background:] Thematic analysis of free-text justifications in human experiments provides significant qualitative insights. Yet, it is costly because reliable annotations require multiple domain experts. Large language models (LLMs) seem…

The performance of large language models (LLMs) is acutely sensitive to the phrasing of prompts, which raises significant concerns about their reliability in real-world scenarios. Existing studies often divide prompts into task-level…

Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise to create sophisticated applications. However, this accessibility extends to…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

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…

Large language models (LLMs) are becoming increasingly integrated into mainstream development platforms and daily technological workflows, typically behind moderation and safety controls. Despite these controls, preventing prompt-based…

Prompt injection evaluations typically treat refusal as a stable, binary indicator of safety. This study challenges that paradigm by modeling refusal as a local decision boundary and examining its stability under structured perturbations.…

The safety and robustness of large language models (LLMs) based applications remain critical challenges in artificial intelligence. Among the key threats to these applications are prompt hacking attacks, which can significantly undermine…

Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…

Large language models (LLMs) are being increasingly integrated into practical hardware and firmware development pipelines for code generation. Existing studies have primarily focused on evaluating the functional correctness of LLM-generated…

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

Evaluating Large Language Model (LLM) applications differs from traditional software testing because outputs are stochastic, high-dimensional, and sensitive to prompt and model changes. We present an evaluation-driven workflow - Define,…

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…

Security analysts face increasing pressure to triage large and complex vulnerability backlogs. Large Language Models (LLMs) offer a potential aid by automating parts of the interpretation process. We evaluate four models (ChatGPT, Claude,…

Large Language Models (LLMs) have demonstrated impressive performance in code generation tasks under idealized conditions, where task descriptions are clear and precise. However, in practice, task descriptions frequently exhibit ambiguity,…

AI-assisted code review is widely used to detect vulnerabilities before production release. Prior work shows that adversarial prompt manipulation can degrade large language model (LLM) performance in code generation. We test whether similar…

As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across…

The widespread adoption of large language models (LLMs) has raised concerns about their safety and reliability, particularly regarding their vulnerability to adversarial attacks. In this paper, we propose a novel perspective that attributes…

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In…