Related papers: Code as a Weapon: A Consensus-Labeled Prompt Bank …

This work considers the problem of resilient consensus where stochastic values of trust between agents are available. Specifically, we derive a unified mathematical framework to characterize convergence, deviation of the consensus from the…

Safety evaluations of language models often treat serving configuration as fixed background infrastructure, but batch condition is an untested treatment variable whenever the same prompt may be evaluated alone, in a synchronized batch, or…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

With their increasing capabilities, Large Language Models (LLMs) are now used across many industries. They have become useful tools for software engineers and support a wide range of development tasks. As LLMs are increasingly used in…

When a user tells an AI system that someone "should not" take an action, the system ought to treat this as a prohibition. Yet many large language models do the opposite: they interpret negated instructions as affirmations. We audited 16…

[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…

Malicious software threats and their detection have been gaining importance as a subdomain of information security due to the expansion of ICT applications in daily settings. A major challenge in designing and developing anti-malware…

Resolving conflicts from merging different software versions is a challenging task. To reduce the overhead of manual merging, researchers develop various program analysis-based tools which only solve specific types of conflicts and have a…

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment often exposes a different class of…

Malicious domains are increasingly common and pose a severe cybersecurity threat. Specifically, many types of current cyber attacks use URLs for attack communications (e.g., C\&C, phishing, and spear-phishing). Despite the continuous…

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 dynamic expansion of social media has led to an inundation of hateful memes on media platforms, accentuating the growing need for efficient identification and removal. Acknowledging the constraints of conventional multimodal hateful…

Large-language-model coding tools are now mainstream in software engineering. But as these same tools move human effort up the development stack, they present fresh dangers: 10% of real prompts leak private data, 42% of generated snippets…

The rapid expansion of research in LLM safety presents challenges in tracking advancements, making benchmarks important evaluation infrastructures for identifying key trends and facilitating systematic comparisons. Yet no systematic…

Large Language Models (LLMs) are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, LLMs could introduce critical vulnerabilities in these systems. Here, we examine…

With the increasing use of large language models (LLMs) in medical decision-support, it is essential to evaluate not only their final answers but also the reliability of their reasoning. Two key risks are Chain-of-Thought (CoT) faithfulness…

Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often…

While the widespread deployment of Large Language Models (LLMs) holds great potential for society, their vulnerabilities to adversarial manipulation and exploitation can pose serious safety, security, and ethical risks. As new threats…

Code reuse is common in modern software development, but it can also spread vulnerabilities when developers unknowingly copy risky code. The code fragments that preserve the logic of known vulnerabilities are known as vulnerable code clones…

Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so does the pressure to ship tasks quickly,…