Related papers: Unsafe Impedance: Safe Languages and Safe by Desig…
Outdated software remains a potent and underappreciated menace in 2025's cybersecurity environment, exposing systems to a broad array of threats, including ransomware, data breaches, and operational outages that can have devastating and…
As large language models (LLMs) see wider real-world use, understanding and mitigating their unsafe behaviors is critical. Interpretation techniques can reveal causes of unsafe outputs and guide safety, but such connections with safety are…
The growing use of Large Language Models (LLMs) for automated code generation has enhanced software development efficiency, but often at the cost of security. Generated code frequently overlooks critical concerns, leaving it vulnerable to…
Uncertain information is being taken into account in an increasing number of application fields. In the meantime, abduction has been proved a powerful tool for handling hypothetical reasoning and incomplete knowledge. Probabilistic logical…
Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…
Rust is a memory-safe programming language that disallows undefined behavior. Its safety guarantees have been extensively examined by the community through empirical studies, which has led to its remarkable success. However, unsafe code…
Safeguard models help large language models (LLMs) detect and block harmful content, but most evaluations remain English-centric and overlook linguistic and cultural diversity. Existing multilingual safety benchmarks often rely on…
Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to different prompt-based attacks, generating harmful content or sensitive information. Both closed-source and open-source LLMs are underinvestigated for these…
Stop words, which are considered non-predictive, are often eliminated in natural language processing tasks. However, the definition of uninformative vocabulary is vague, so most algorithms use general knowledge-based stop lists to remove…
Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs possess a much stronger capability for semantic understanding, enabling them to…
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass…
Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries--a phenomenon known as overrefusal. Overrefusal typically stems from over-conservative…
Some approaches to increasing program reliability involve a disciplined use of programming languages so as to minimise the hazards introduced by error-prone features. This is realised by writing code that is constrained to a subset of the a…
Cyber assurance, which is the ability to operate under the onslaught of cyber attacks and other unexpected events, is essential for organizations facing inundating security threats on a daily basis. Organizations usually employ multiple…
Organizational cybersecurity policies are often examined to determine whether they adequately comply standard security controls. This task is difficult because control statements are abstract, whereas policy documents describe governance…
When AI systems are granted the agency to take impactful actions in the real world, there is an inherent risk that these systems behave in ways that are harmful. Typically, humans specify constraints on the AI system to prevent harmful…
Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficult to tailor responses to diverse application needs. %As a…
Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…
Organizations are rapidly adopting Large Language Models (LLMs) to transform their operations, yet they lack clear guidance on key decisions for adoption and implementation. While LLMs offer powerful capabilities in content generation,…
It is well-known that Microsoft Word/Excel compatible documents or PDF files can contain malicious content. LaTeX files are unfortunately no exception either. LaTeX users often include third-party codes through sources or packages (.sty or…