Related papers: When Scanners Lie: Evaluator Instability in LLM Re…

LLM-based agents show promise for automating penetration testing, yet reported performance varies widely across systems and benchmarks. We analyze 28 LLM-based penetration testing systems and evaluate five representative implementations…

The increasing adoption of Large Language Models (LLMs) in software engineering has sparked interest in their use for software vulnerability detection. However, the rapid development of this field has resulted in a fragmented research…

As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of these systems is paramount. However, AI is currently facing a reproducibility crisis driven…

Peer review is essential for maintaining academic quality, but the increasing volume of submissions places a significant burden on reviewers. Large language models (LLMs) offer potential assistance in this process, yet their susceptibility…

Proactive interventions by LLM critic models are often assumed to improve reliability, yet their effects at deployment time are poorly understood. We show that a binary LLM critic with strong offline accuracy (AUROC 0.94) can nevertheless…

Large Language Models (LLMs) show promise for automated grading, but their outputs can be unreliable. Rather than improving grading accuracy directly, we address a complementary problem: \textit{predicting when an LLM grader is likely to be…

User authentication and fraud detection face growing challenges as digital systems expand and adversaries adopt increasingly sophisticated tactics. Traditional knowledge-based authentication remains rigid, requiring exact word-for-word…

The indexing-retrieval-generation paradigm of retrieval-augmented generation (RAG) has been highly successful in solving knowledge-intensive tasks by integrating external knowledge into large language models (LLMs). However, the…

Reasoning failures in large language models (LLMs) are typically measured only at the end of a generation, yet many failures manifest as a process-level breakdown: the model "loses the thread" mid-reasoning. We study whether such breakdowns…

Current state-of-the-art automatic software repair (ASR) techniques rely heavily on incomplete specifications, e.g., test suites, to generate repairs. This, however, may render ASR tools to generate incorrect repairs that do not generalize.…

Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the…

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

Despite various approaches being employed to detect vulnerabilities, the number of reported vulnerabilities shows an upward trend over the years. This suggests the problems are not caught before the code is released, which could be caused…

As machine learning (ML) systems increasingly permeate high-stakes settings such as healthcare, transportation, military, and national security, concerns regarding their reliability have emerged. Despite notable progress, the performance of…

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

Static Application Security Testing (SAST) tools are essential for identifying software vulnerabilities, but they often produce a high volume of false positives (FPs), imposing a substantial manual triage burden on developers. Recent…

Automatic Speech Recognition (ASR) error correction aims to correct recognition errors while preserving accurate text. Although traditional approaches demonstrate moderate effectiveness, LLMs offer a paradigm that eliminates the need for…

LLM-as-judge frameworks are increasingly used for automatic NLG evaluation, yet their per-instance reliability remains poorly understood. We present a two-pronged diagnostic toolkit applied to SummEval: $\textbf{(1)}$ a transitivity…

Some prior work has shown that LLMs perform well in NLG evaluation for different tasks. However, we discover that LLMs seem to confuse different evaluation criteria, which reduces their reliability. For further verification, we first…

AI-enabled Security Orchestration, Automation, and Response (SOAR) systems increasingly employ autonomous agents for cyber defense, yet their resilience to adaptive adversaries is underexplored. We introduce an autonomous red teaming…