Related papers: Unsafe Impedance: Safe Languages and Safe by Desig…

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

The prevalence of security vulnerabilities has prompted companies to adopt static application security testing (SAST) tools for vulnerability detection. Nevertheless, these tools frequently exhibit usability limitations, as their generic…

Large language models (LLMs) for code are typically trained to align with natural language instructions to closely follow their intentions and requirements. However, in many practical scenarios, it becomes increasingly challenging for these…

We propose a new formal criterion for secure compilation, providing strong security guarantees for components written in unsafe, low-level languages with C-style undefined behavior. Our criterion goes beyond recent proposals, which protect…

Security threats like prompt injection attacks pose significant risks to applications that integrate Large Language Models (LLMs), potentially leading to unauthorized actions such as API misuse. Unlike previous approaches that aim to detect…

Software has become an integral part of everyday life. Everyday, millions of people perform transaction through internet, ATM, mobile phone, they send email and Egreetings, and use word processing and spreadsheet for various purpose. People…

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

As Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications, their safety concerns become critical areas of NLP research. This paper presents Safety and Over-Defensiveness Evaluation (SODE)…

We give a rigorous characterization of what it means for a programming language to be memory safe, capturing the intuition that memory safety supports local reasoning about state. We formalize this principle in two ways. First, we show how…

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets…

Software reliability is critical in ensuring that the digital systems we depend on function correctly. In software development, increasing software reliability often involves testing. However, for complex and critical systems, developers…

Enterprise customers are increasingly adopting Large Language Models (LLMs) for critical communication tasks, such as drafting emails, crafting sales pitches, and composing casual messages. Deploying such models across different regions…

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…

The rise of "jailbreak" attacks on language models has led to a flurry of defenses aimed at preventing undesirable responses. We critically examine the two stages of the defense pipeline: (i) defining what constitutes unsafe outputs, and…

Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such type of safety that has been scarcely studied is commonsense…

Large language models (LLMs) are being deployed across the Global South, where everyday use involves low-resource languages, code-mixing, and culturally specific norms. Yet safety pipelines, benchmarks, and alignment still largely target…

The emergence of vibe coding, a paradigm where non-technical users instruct Large Language Models (LLMs) to generate executable codes via natural language, presents both significant opportunities and severe risks for the construction…

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…

Large language models are increasingly used as planners for robotic systems, yet how safely they plan remains an open question. To evaluate safe planning systematically, we introduce DESPITE, a benchmark of 12,279 tasks spanning physical…