Related papers: DynaGuard: A Dynamic Guardian Model With User-Defi…

With the growing deployment of large language models (LLMs) in real-world applications, establishing robust safety guardrails to moderate their inputs and outputs has become essential to ensure adherence to safety policies. Current…

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

The modern web stack, which is dominated by browser-based applications and API-first backends, now operates under an adversarial equilibrium where automated, AI-assisted attacks evolve continuously. Content Delivery Networks (CDNs) and edge…

The proliferation of AI technology gives rise to a variety of security threats, which significantly compromise the confidentiality and integrity of AI models and applications. Existing software-based solutions mainly target one specific…

Leveraging machine learning methods to solve constraint satisfaction problems has shown promising, but they are mostly limited to a static situation where the problem description is completely known and fixed from the beginning. In this…

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…

AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…

It is well recognised that ensuring fair AI systems is a complex sociotechnical challenge, which requires careful deliberation and continuous oversight across all stages of a system's lifecycle, from defining requirements to model…

In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can…

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Evaluating the safety of AI Systems is a pressing concern for organizations deploying them. In addition to the societal damage done by the lack of fairness of those systems, deployers are concerned about the legal repercussions and the…

Security-critical system requirements are increasingly enforced through mandatory access control systems. These systems are controlled by security policies, highly sensitive system components, which emphasizes the paramount importance of…

Language model deployments in consumer-facing applications introduce numerous risks. While existing research on harms and hazards of such applications follows top-down approaches derived from regulatory frameworks and theoretical analyses,…

Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core…

Humans develop a series of cognitive defenses, known as epistemic vigilance, to combat risks of deception and misinformation from everyday interactions. Developing safeguards for LLMs inspired by this mechanism might be particularly helpful…

Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are…

Experts in Artificial Intelligence (AI) development predict that advances in the development of intelligent systems and agents will reshape vital areas in our society. Nevertheless, if such an advance isn't done with prudence, it can result…

Metaverse is trending to create a digital circumstance that can transfer the real world to an online platform supported by large quantities of real-time interactions. Pre-trained Artificial Intelligence (AI) models are demonstrating their…

A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate runtime knowledge acquisition. Model-checking and automated…

Reasoning models have demonstrated remarkable capabilities in complex reasoning tasks. However, ensuring their safety against adversarial jailbreak prompts remains a critical challenge. Due to the covert and deceptive nature of such…