English
Related papers

Related papers: Obfuscated Activations Bypass LLM Latent-Space Def…

200 papers

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

Cryptography and Security · Computer Science 2025-06-13 Kaiyuan Zhang , Siyuan Cheng , Hanxi Guo , Yuetian Chen , Zian Su , Shengwei An , Yuntao Du , Charles Fleming , Ashish Kundu , Xiangyu Zhang , Ninghui Li

Passive operating system fingerprinting reveals valuable information to the defenders of heterogeneous private networks; at the same time, attackers can use fingerprinting to reconnoiter networks, so defenders need obfuscation techniques to…

Cryptography and Security · Computer Science 2017-06-27 Blake Anderson , David McGrew

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…

Machine Learning · Computer Science 2021-06-10 Boxi Wu , Heng Pan , Li Shen , Jindong Gu , Shuai Zhao , Zhifeng Li , Deng Cai , Xiaofei He , Wei Liu

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…

Cryptography and Security · Computer Science 2025-12-09 Sarthak Choudhary , Divyam Anshumaan , Nils Palumbo , Somesh Jha

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during…

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…

Cryptography and Security · Computer Science 2025-06-02 Xin Yi , Yue Li , Dongsheng Shi , Linlin Wang , Xiaoling Wang , Liang He

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…

Cryptography and Security · Computer Science 2026-05-05 Lingxi Zhang , Guangtao Zheng , Hanjie Chen

As large language models are increasingly deployed in sensitive environments, fingerprinting attacks pose significant privacy and security risks. We present a study of LLM fingerprinting from both offensive and defensive perspectives. Our…

Cryptography and Security · Computer Science 2025-08-13 Kevin Kurian , Ethan Holland , Sean Oesch

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

Computation and Language · Computer Science 2025-04-18 Charlotte Siska , Anush Sankaran

Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trigger refusal while preserving benign utility.…

Cryptography and Security · Computer Science 2026-05-26 Luoyu Chen , Weiqi Wang , Zhiyi Tian , Chenhan Zhang , Feng Wu , Jianhuan Huang , Ahmed Asiri , Shui Yu

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively…

Cryptography and Security · Computer Science 2025-07-30 Stephen Casper , Lennart Schulze , Oam Patel , Dylan Hadfield-Menell

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

Cryptography and Security · Computer Science 2026-05-14 Priyal Deep , Shane Emmons , Amy Fox , Kyle Bacon , Kelley McAllister , Peter Ortiz , Krisztian Flautner

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

Federated Learning (FL) has garnered significant attention for its potential to protect user privacy while enhancing model training efficiency. For that reason, FL has found its use in various domains, from healthcare to industrial…

Cryptography and Security · Computer Science 2024-06-05 Tre' R. Jeter , Truc Nguyen , Raed Alharbi , My T. Thai

As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts.…

Computation and Language · Computer Science 2025-08-19 Xinbo Wu , Abhishek Umrawal , Lav R. Varshney

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

Artificial Intelligence · Computer Science 2025-05-21 Maheep Chaudhary , Fazl Barez

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

Cryptography and Security · Computer Science 2026-03-18 Ali Raza , Gurang Gupta , Nikolay Matyunin , Jibesh Patra

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…