English
Related papers

Related papers: SafetyAnalyst: Interpretable, Transparent, and Ste…

200 papers

Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence…

Computers and Society · Computer Science 2025-09-24 Luis Enriquez Alvarez

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Cryptography and Security · Computer Science 2026-04-03 Nanxi Li , Zhengyue Zhao , G. Edward Suh , Marco Pavone , Chaowei Xiao

The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety and AI security. Although the two disciplines now come…

The rise of artificial intelligence (AI) as super-capable assistants has transformed productivity and decision-making across domains. Yet, this integration raises critical concerns about value alignment - ensuring AI behaviors remain…

Artificial Intelligence · Computer Science 2025-10-07 Santhosh Kumar Ravindran

Amidst escalating concerns about the detriments inflicted by AI systems, risk management assumes paramount importance, notably for high-risk applications as demanded by the European Union AI Act. Guidelines provided by ISO and NIST aim to…

Computers and Society · Computer Science 2024-06-19 sundaraparipurnan Narayanan , Sandeep Vishwakarma

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…

Cryptography and Security · Computer Science 2026-04-09 Hongyi Lu , Nian Liu , Shuai Wang , Fengwei Zhang

Safety-aligned language models often exhibit fragile and imbalanced safety mechanisms, increasing the likelihood of generating unsafe content. In addition, incorporating new knowledge through editing techniques to language models can…

Computation and Language · Computer Science 2024-12-17 Somnath Banerjee , Sayan Layek , Soham Tripathy , Shanu Kumar , Animesh Mukherjee , Rima Hazra

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused…

Cryptography and Security · Computer Science 2026-03-24 Marco Arazzi , Vignesh Kumar Kembu , Antonino Nocera

We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful content and screen adversarial prompts in human-AI conversational settings. The first component,…

Computation and Language · Computer Science 2025-11-18 JoonHo Lee , HyeonMin Cho , Jaewoong Yun , Hyunjae Lee , JunKyu Lee , Juree Seok

AI policy guidance is predominantly written as prose, which practitioners must first convert into executable rules before frameworks can evaluate or enforce them. This manual step is slow, error-prone, difficult to scale, and often delays…

Artificial Intelligence · Computer Science 2025-12-05 Gautam Varma Datla , Anudeep Vurity , Tejaswani Dash , Tazeem Ahmad , Mohd Adnan , Saima Rafi

Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet researchers, policymakers, and technology companies lack shared terminology for discussing AI risks.…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Artificial Intelligence · Computer Science 2025-08-13 Shivam Dubey

Millions of users now design personalized LLM-based chatbots that shape their daily interactions, yet they can only roughly anticipate how their design choices will manifest as behaviors in deployment. This opacity is consequential:…

Human-Computer Interaction · Computer Science 2025-11-25 Sheer Karny , Anthony Baez , Pat Pataranutaporn

In this paper we discuss how systems with Artificial Intelligence (AI) can undergo safety assessment. This is relevant, if AI is used in safety related applications. Taking a deeper look into AI models, we show, that many models of…

Artificial Intelligence · Computer Science 2021-05-17 Jens Braband , Hendrik Schäbe

Artificial intelligence (AI) is increasingly embedded in NHS workflows, but its probabilistic and adaptive behaviour conflicts with the deterministic assumptions underpinning existing clinical-safety standards. DCB0129 and DCB0160 provide…

Computers and Society · Computer Science 2025-11-19 Robert Gigiu

We evaluate how effectively platform-level parental controls moderate a mainstream conversational assistant used by minors. Our two-phase protocol first builds a category-balanced conversation corpus via PAIR-style iterative prompt…

Computers and Society · Computer Science 2026-02-02 Kerem Ersoz , Saleh Afroogh , David Atkinson , Junfeng Jiao

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Cryptography and Security · Computer Science 2025-05-30 Jinchuan Zhang , Lu Yin , Yan Zhou , Songlin Hu

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Machine Learning · Computer Science 2025-07-04 Mary Phuong , Roland S. Zimmermann , Ziyue Wang , David Lindner , Victoria Krakovna , Sarah Cogan , Allan Dafoe , Lewis Ho , Rohin Shah

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

Large language models (LLMs) remain vulnerable to misalignment and jailbreaks, making external safeguards like moderation filters essential, yet existing filters often focus narrowly on safety, falling short of the broader alignment needs…

Computation and Language · Computer Science 2026-01-08 Masoomali Fatehkia , Enes Altinisik , Mohamed Osman , Husrev Taha Sencar