English
Related papers

Related papers: Jailbreaking is (Mostly) Simpler Than You Think

200 papers

Generative AI models perturb the foundations of effective human communication. They present new challenges to contextual confidence, disrupting participants' ability to identify the authentic context of communication and their ability to…

Artificial Intelligence · Computer Science 2024-01-26 Shrey Jain , Zoë Hitzig , Pamela Mishkin

Current research on operator control of Large Language Models improves model robustness against adversarial attacks and misbehavior by training on preference examples, prompting, and input/output filtering. Despite good results, LLMs remain…

Artificial Intelligence · Computer Science 2025-12-03 Thomas Rivasseau

Low-Rank Adaptation (LoRA) has emerged as an efficient method for fine-tuning large language models (LLMs) and is widely adopted within the open-source community. However, the decentralized dissemination of LoRA adapters through platforms…

Cryptography and Security · Computer Science 2025-12-23 Linzhi Chen , Yang Sun , Hongru Wei , Yuqi Chen

Adversarial behavior plays a central role in aligning large language models with human values. However, existing alignment methods largely rely on static adversarial settings, which fundamentally limit robustness, particularly in multimodal…

Cryptography and Security · Computer Science 2026-03-03 Guoxin Shi , Haoyu Wang , Zaihui Yang , Yuxing Wang , Yongzhe Chang

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Cryptography and Security · Computer Science 2025-07-15 Joshua Kazdan , Abhay Puri , Rylan Schaeffer , Lisa Yu , Chris Cundy , Jason Stanley , Sanmi Koyejo , Krishnamurthy Dvijotham

The Model Context Protocol (MCP) replaces static, developer-controlled API integrations with more dynamic, user-driven agent systems, which also introduces new security risks. As MCP adoption grows across community servers and major…

Cryptography and Security · Computer Science 2025-11-27 Herman Errico , Jiquan Ngiam , Shanita Sojan

Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robot itself, and…

Robotics · Computer Science 2026-04-21 Borong Zhang , Yuhao Zhang , Jiaming Ji , Yingshan Lei , Yishuai Cai , Josef Dai , Yuanpei Chen , Yaodong Yang

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Cryptography and Security · Computer Science 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan

Recent advancements in AI safety have led to increased efforts in training and red-teaming large language models (LLMs) to mitigate unsafe content generation. However, these safety mechanisms may not be comprehensive, leaving potential…

Cryptography and Security · Computer Science 2024-11-06 Emet Bethany , Mazal Bethany , Juan Arturo Nolazco Flores , Sumit Kumar Jha , Peyman Najafirad

AI Accelerator (AIA) are specialized hardware e.g., Tensor Processing Unit (TPU), that enable optimal and efficient execution of AI applications and on-device inference. The growing demand for AI applications has led to the widespread…

Cryptography and Security · Computer Science 2026-05-19 Datta Manikanta Sri Hari Danduri , Aravind Kumar Machiry

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulnerable to jailbreak attacks that bypass safety guardrails.…

Cryptography and Security · Computer Science 2025-04-29 Julien Piet , Xiao Huang , Dennis Jacob , Annabella Chow , Maha Alrashed , Geng Zhao , Zhanhao Hu , Chawin Sitawarin , Basel Alomair , David Wagner

Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, often framing risks as adversarial events and relying on…

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…

Artificial Intelligence · Computer Science 2026-01-08 Kanghua Mo , Li Hu , Yucheng Long , Zhihao Li

Modern software-defined networks, such as Open Radio Access Network (O-RAN) systems, rely on artificial intelligence (AI)-powered applications running on controllers interfaced with the radio access network. To ensure that these AI…

Signal Processing · Electrical Eng. & Systems 2025-02-06 Seonghoon Yoo , Sangwoo Park , Petar Popovski , Joonhyuk Kang , Osvaldo Simeone

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss. The only known robust defense is architectural isolation that strictly separates trusted task…

Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…

Cryptography and Security · Computer Science 2025-07-30 Gauri Sharma , Vidhi Kulkarni , Miles King , Ken Huang

The development of artificial intelligence demands that models incrementally update knowledge by Continual Learning (CL) to adapt to open-world environments. To meet privacy and security requirements, Continual Unlearning (CU) emerges as an…

Content composition vulnerabilities remain among the most prevalent and persistent classes of security weakness in deployed software. Prior mitigations, including developer training, static analysis tools, and domain-specific template…

Programming Languages · Computer Science 2026-05-19 Mike Samuel , Tom Palmer , Shaw Summa , Robert Grayson

Embedded into information systems, artificial intelligence (AI) faces security threats that exploit AI-specific vulnerabilities. This paper provides an accessible overview of adversarial attacks unique to predictive and generative AI…

Cryptography and Security · Computer Science 2025-07-01 Naoto Kiribuchi , Kengo Zenitani , Takayuki Semitsu

Harm reporting in Artificial Intelligence (AI) currently lacks a structured process for disclosing and addressing algorithmic flaws, relying largely on an ad-hoc approach. This contrasts sharply with the well-established Coordinated…

Artificial Intelligence · Computer Science 2024-07-29 Sven Cattell , Avijit Ghosh , Lucie-Aimée Kaffee