English
Related papers

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

200 papers

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Machine Learning · Computer Science 2025-07-08 Xin Wei Chia , Swee Liang Wong , Jonathan Pan

Latent-space monitors aim to detect undesirable behaviours in Large Language Models by leveraging their internal representations rather than relying solely on black-box outputs. These methods have shown promise in identifying behaviours…

Machine Learning · Computer Science 2026-02-27 Rohan Gupta , Erik Jenner

We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative…

Machine Learning · Computer Science 2018-08-01 Anish Athalye , Nicholas Carlini , David Wagner

The widespread adoption of Large Language Models (LLMs) in critical applications has introduced severe reliability and security risks, as LLMs remain vulnerable to notorious threats such as hallucinations, jailbreak attacks, and backdoor…

Cryptography and Security · Computer Science 2026-04-07 Shide Zhou , Kailong Wang , Ling Shi , Haoyu Wang

Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to…

Machine Learning · Computer Science 2020-09-29 Giulio Zizzo , Chris Hankin , Sergio Maffeis , Kevin Jones

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…

Computation and Language · Computer Science 2025-02-24 Tianlong Li , Zhenghua Wang , Wenhao Liu , Muling Wu , Shihan Dou , Changze Lv , Xiaohua Wang , Xiaoqing Zheng , Xuanjing Huang

Large language models (LLMs) can be misused to reveal sensitive information, such as weapon-making instructions or writing malware. LLM providers rely on $\emph{monitoring}$ to detect and flag unsafe behavior during inference. An open…

Cryptography and Security · Computer Science 2026-04-01 Toluwani Aremu , Daniil Ognev , Samuele Poppi , Nils Lukas

Latent-based multi-agent systems replace parts of explicit inter-agent communication with hidden representations, offering a new direction for efficient and flexible agent collaboration. However, moving coordination into latent space may…

Cryptography and Security · Computer Science 2026-05-28 Chenxi Wang , Ruiyang Huang , Jiayan Sun , Lei Wei , Yifan Wu

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…

Deploying DL models on mobile Apps has become ever-more popular. However, existing studies show attackers can easily reverse-engineer mobile DL models in Apps to steal intellectual property or generate effective attacks. A recent approach,…

Software Engineering · Computer Science 2024-10-22 Mingyi Zhou , Xiang Gao , Xiao Chen , Chunyang Chen , John Grundy , Li Li

Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack strategies, there is no unified understanding on why some…

Computation and Language · Computer Science 2024-12-04 Yuping Lin , Pengfei He , Han Xu , Yue Xing , Makoto Yamada , Hui Liu , Jiliang Tang

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Cryptography and Security · Computer Science 2022-05-31 Sangeet Sagar , Abhinav Bhatt , Abhijith Srinivas Bidaralli

In recent years, Deep Neural Network models have been developed in different fields, where they have brought many advances. However, they have also started to be used in tasks where risk is critical. A misdiagnosis of these models can lead…

Machine Learning · Computer Science 2024-02-13 Xabier Echeberria-Barrio , Amaia Gil-Lerchundi , Jon Egana-Zubia , Raul Orduna-Urrutia

Intent obfuscation is a common tactic in adversarial situations, enabling the attacker to both manipulate the target system and avoid culpability. Surprisingly, it has rarely been implemented in adversarial attacks on machine learning…

Cryptography and Security · Computer Science 2024-08-30 Zhaobin Li , Patrick Shafto

Federated learning is considered as an effective privacy-preserving learning mechanism that separates the client's data and model training process. However, federated learning is still under the risk of privacy leakage because of the…

Machine Learning · Computer Science 2022-06-03 Yuxuan Wan , Han Xu , Xiaorui Liu , Jie Ren , Wenqi Fan , Jiliang Tang

Side-channel attacks that use machine learning (ML) for signal analysis have become prominent threats to computer security, as ML models easily find patterns in signals. To address this problem, this paper explores using Adversarial Machine…

Cryptography and Security · Computer Science 2023-10-17 Hyoungwook Nam , Raghavendra Pradyumna Pothukuchi , Bo Li , Nam Sung Kim , Josep Torrellas

As large language models (LLMs) continue to evolve, their potential use in automating cyberattacks becomes increasingly likely. With capabilities such as reconnaissance, exploitation, and command execution, LLMs could soon become integral…

Cryptography and Security · Computer Science 2024-10-22 Daniel Ayzenshteyn , Roy Weiss , Yisroel Mirsky

Prompt injection attacks pose significant risks to language model safety, yet existing defenses are typically evaluated using classification performance. We show that high detection performance does not imply representational robustness.…

Cryptography and Security · Computer Science 2026-05-20 Becky Mashaido , Tapadhir Das

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by…

Machine Learning · Computer Science 2026-05-27 Kevin Kuo , Chhavi Yadav , Virginia Smith

To avoid detection, adversaries often use command-line obfuscation. There are numerous techniques of the command-line obfuscation, all designed to alter the command-line syntax without affecting its original functionality. This variability…

Cryptography and Security · Computer Science 2024-08-06 Vojtech Outrata , Michael Adam Polak , Martin Kopp
‹ Prev 1 2 3 10 Next ›