English
Related papers

Related papers: SafeRedirect: Defeating Internal Safety Collapse v…

200 papers

Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm…

Cryptography and Security · Computer Science 2025-06-17 Chen Yueh-Han , Nitish Joshi , Yulin Chen , Maksym Andriushchenko , Rico Angell , He He

Large Language Models (LLMs) have demonstrated remarkable capabilities in performing tasks across various domains without needing explicit retraining. This capability, known as In-Context Learning (ICL), while impressive, exposes LLMs to a…

Computation and Language · Computer Science 2024-10-16 Bibek Upadhayay , Vahid Behzadan , Amin Karbasi

With the widespread real-world deployment of large language models (LLMs), ensuring their behavior complies with safety standards has become crucial. Jailbreak attacks exploit vulnerabilities in LLMs to induce undesirable behavior, posing a…

Computation and Language · Computer Science 2025-05-26 Jiaqi Wu , Chen Chen , Chunyan Hou , Xiaojie Yuan

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

Cryptography and Security · Computer Science 2026-02-09 Sizhe Chen , Arman Zharmagambetov , David Wagner , Chuan Guo

Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversational safety mechanisms. We introduce Incremental Completion Decomposition (ICD), a…

Computation and Language · Computer Science 2026-04-30 Samee Arif , Naihao Deng , Zhijing Jin , Rada Mihalcea

Large language models (LLMs) are promising tools for supporting security management tasks, such as incident response planning. However, their unreliability and tendency to hallucinate remain significant challenges. In this paper, we address…

Artificial Intelligence · Computer Science 2026-02-06 Kim Hammar , Tansu Alpcan , Emil Lupu

Industrial control system (ICS) operations use trusted endpoints like human machine interfaces (HMIs) and workstations to relay commands to programmable logic controllers (PLCs). Because most PLCs lack layered defenses, compromise of a…

Cryptography and Security · Computer Science 2025-10-09 Rishabh Das. Aaron Werth , Tommy Morris

Modern code completion engines, powered by large language models (LLMs), assist millions of developers with their strong capabilities to generate functionally correct code. Due to this popularity, it is crucial to investigate the security…

Cryptography and Security · Computer Science 2025-06-16 Slobodan Jenko , Niels Mündler , Jingxuan He , Mark Vero , Martin Vechev

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

Cryptography and Security · Computer Science 2025-09-29 Xiyu Zeng , Siyuan Liang , Liming Lu , Haotian Zhu , Enguang Liu , Jisheng Dang , Yongbin Zhou , Shuchao Pang

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction…

Machine Learning · Computer Science 2026-05-28 Amir Moeini , Minjae Kwon , Alper Kamil Bozkurt , Yuichi Motai , Rohan Chandra , Lu Feng , Shangtong Zhang

Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional components. However, existing safety attribution methods…

Machine Learning · Computer Science 2026-03-25 Miao Yu , Siyuan Fu , Moayad Aloqaily , Zhenhong Zhou , Safa Otoum , Xing fan , Kun Wang , Yufei Guo , Qingsong Wen

Large language models (LLMs) for Verilog code generation are increasingly adopted in hardware design, yet remain vulnerable to backdoor attacks where adversaries inject malicious triggers during training to induce vulnerable hardware…

Software Engineering · Computer Science 2026-02-05 Guang Yang , Xing Hu , Xiang Chen , Xin Xia

LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination…

Cryptography and Security · Computer Science 2026-03-12 Yu He , Haozhe Zhu , Yiming Li , Shuo Shao , Hongwei Yao , Zhihao Liu , Zhan Qin

In modern software development, multiple software components, often sourced from different contributors, including AI assistants, are combined to create a cohesive system. Although these components might each be individually safe, their…

Software Engineering · Computer Science 2024-10-25 Peisen Lin , Yuntong Zhang , Andreea Costea , Abhik Roychoudhury

The security of Industrial Control Systems (ICS) has been attracting increased attention over the past years, following the discovery of real threats targeting industrial environments. Despite this attention, automation of the reverse…

Cryptography and Security · Computer Science 2020-01-20 Anastasis Keliris , Michail Maniatakos

Intellectual Property (IP) theft is a serious concern for the integrated circuit (IC) industry. To address this concern, logic locking countermeasure transforms a logic circuit to a different one to obfuscate its inner details. The…

Cryptography and Security · Computer Science 2021-02-18 Qinhan Tan , Seetal Potluri , Aydin Aysu

The application of large language models to code generation has evolved from one-shot generation to iterative refinement, yet the evolution of security throughout iteration remains insufficiently understood. Through comparative experiments…

Cryptography and Security · Computer Science 2026-03-10 Yi Chen , Yun Bian , Haiquan Wang , Shihao Li , Zhe Cui

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…

Cryptography and Security · Computer Science 2026-02-26 David Schmotz , Luca Beurer-Kellner , Sahar Abdelnabi , Maksym Andriushchenko

LLM-based SOC log classifiers are commonly evaluated using regular-expression pipelines that extract structured fields from free-form model output. We demonstrate that this practice introduces a class of silent, systematic evaluation…

Cryptography and Security · Computer Science 2026-05-11 Chaitanya Vilas Garware , Sharif Noor Zisad