English
Related papers

Related papers: Dynamic Adversarial Fine-Tuning Reorganizes Refusa…

200 papers

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

Machine Learning · Computer Science 2026-05-05 Sadia Asif , Mohammad Mohammadi Amiri

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Cryptography and Security · Computer Science 2025-09-19 Yuanbo Xie , Yingjie Zhang , Tianyun Liu , Duohe Ma , Tingwen Liu

Learning-to-Defer (L2D) enables hybrid decision-making by routing inputs either to a predictor or to external experts. While promising, L2D is highly vulnerable to adversarial perturbations, which can not only flip predictions but also…

Machine Learning · Statistics 2026-05-29 Yannis Montreuil , Letian Yu , Axel Carlier , Lai Xing Ng , Wei Tsang Ooi

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Computation and Language · Computer Science 2025-10-08 Harethah Abu Shairah , Hasan Abed Al Kader Hammoud , Bernard Ghanem , George Turkiyyah

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Computation and Language · Computer Science 2021-12-23 Xinhsuai Dong , Luu Anh Tuan , Min Lin , Shuicheng Yan , Hanwang Zhang

Reinforcement learning (RL) fine-tuning transforms large language models while creating a vulnerability we experimentally verify: Our experiment shows that malicious RL fine-tuning dismantles safety guardrails with remarkable efficiency,…

Machine Learning · Computer Science 2025-05-08 Wenjun Cao

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song

Safety-aligned large language models (LLMs) remain vulnerable to backdoor attacks. Recent model editing-based approaches enable efficient backdoor injection by directly modifying a small set of parameters to map triggers to attacker-desired…

Computation and Language · Computer Science 2026-03-25 Houcheng Jiang , Zetong Zhao , Junfeng Fang , Haokai Ma , Ruipeng Wang , Xiang Wang , Xiangnan He , Yang Deng

Recent work has shown that language models' refusal behavior is primarily encoded in a single direction in their latent space, making it vulnerable to targeted attacks. Although Latent Adversarial Training (LAT) attempts to improve…

Computation and Language · Computer Science 2025-04-29 Alexandra Abbas , Nora Petrova , Helios Ael Lyons , Natalia Perez-Campanero

Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests.…

Cryptography and Security · Computer Science 2026-01-13 Shawn Li , Chenxiao Yu , Zhiyu Ni , Hao Li , Charith Peris , Chaowei Xiao , Yue Zhao

Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Yaguan Qian , Chenyu Zhao , Zhaoquan Gu , Bin Wang , Shouling Ji , Wei Wang , Boyang Zhou , Pan Zhou

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

Cryptography and Security · Computer Science 2026-05-26 Itay Zloczower , Eyal Lenga , Gilad Gressel , Yisroel Mirsky

Deep Learning (DL) methods have shown promising results for solving ill-posed inverse problems such as MR image reconstruction from undersampled $k$-space data. However, these approaches currently have no guarantees for reconstruction…

Image and Video Processing · Electrical Eng. & Systems 2022-08-08 Jan Nikolas Morshuis , Sergios Gatidis , Matthias Hein , Christian F. Baumgartner

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…

Machine Learning · Computer Science 2019-11-28 Chao Tang , Yifei Fan , Anthony Yezzi

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…

Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex scenes. This weakness stems from a reliance on finite training datasets, which are…

Machine Learning · Computer Science 2026-03-05 Yicheng Bao , Xuhong Wang , Qiaosheng Zhang , Chaochao Lu , Xia Hu , Xin Tan

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Computation and Language · Computer Science 2026-04-29 Nirmalendu Prakash , Yeo Wei Jie , Amir Abdullah , Ranjan Satapathy , Erik Cambria , Roy Ka Wei Lee

Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correlates well with the qualitative assessment of the attacks. We…

Computer Vision and Pattern Recognition · Computer Science 2018-06-13 George Gondim-Ribeiro , Pedro Tabacof , Eduardo Valle

Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input. Given that that emerging physical systems are using DNNs in…

Cryptography and Security · Computer Science 2018-04-11 Kevin Eykholt , Ivan Evtimov , Earlence Fernandes , Bo Li , Amir Rahmati , Chaowei Xiao , Atul Prakash , Tadayoshi Kohno , Dawn Song

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have…

Cryptography and Security · Computer Science 2021-03-16 Zhe Zhao , Guangke Chen , Jingyi Wang , Yiwei Yang , Fu Song , Jun Sun
‹ Prev 1 2 3 10 Next ›