English
Related papers

Related papers: An Adversarial Perspective on Machine Unlearning f…

200 papers

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

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

When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Ivan Evtimov , Ian Covert , Aditya Kusupati , Tadayoshi Kohno

The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawful content. This has accelerated the push for machine…

Machine Learning · Computer Science 2025-11-26 Agnieszka Polowczyk , Alicja Polowczyk , Joanna Waczyńska , Piotr Borycki , Przemysław Spurek

Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks. However, their static deployment conflicts with growing societal and regulatory demands --…

In this work, we demonstrate that certain machine unlearning methods may fail under straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families using output-based, logit-based, and…

Cryptography and Security · Computer Science 2025-08-15 Yeonwoo Jang , Shariqah Hossain , Ashwin Sreevatsa , Diogo Cruz

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…

Machine Learning · Computer Science 2020-07-07 Samuel Henrique Silva , Peyman Najafirad

The widespread popularity of Large Language Models (LLMs), partly due to their unique ability to perform in-context learning, has also brought to light the importance of ethical and safety considerations when deploying these pre-trained…

Computation and Language · Computer Science 2024-08-07 Karuna Bhaila , Minh-Hao Van , Xintao Wu

This research provides a comprehensive overview of adversarial attacks on AI and ML models, exploring various attack types, techniques, and their potential harms. We also delve into the business implications, mitigation strategies, and…

In order to adhere to regulatory standards governing individual data privacy and safety, machine learning models must systematically eliminate information derived from specific subsets of a user's training data that can no longer be…

Machine Learning · Computer Science 2024-03-26 Subhodip Panda , Shashwat Sourav , Prathosh A. P

Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both generating a set of examples and running iterations of…

Computation and Language · Computer Science 2024-06-12 Pratiksha Thaker , Yash Maurya , Shengyuan Hu , Zhiwei Steven Wu , Virginia Smith

Recent legal frameworks have mandated the right to be forgotten, obligating the removal of specific data upon user requests. Machine Unlearning has emerged as a promising solution by selectively removing learned information from machine…

Machine Learning · Computer Science 2025-05-14 Xiang Li , Bhavani Thuraisingham , Wenqi Wei

Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make…

Machine Learning · Computer Science 2018-10-24 Guofu Li , Pengjia Zhu , Jin Li , Zhemin Yang , Ning Cao , Zhiyi Chen

Adversarial examples are inputs to a machine learning system that result in an incorrect output from that system. Attacks launched through this type of input can cause severe consequences: for example, in the field of image recognition, a…

Machine Learning · Computer Science 2021-11-24 Stefano Cresci , Marinella Petrocchi , Angelo Spognardi , Stefano Tognazzi

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

Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in capabilities, behavioral profile, and internal failure mode. We study behavioral and mechanistic…

Cryptography and Security · Computer Science 2026-04-21 Md Rysul Kabir , Zoran Tiganj

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

Computation and Language · Computer Science 2025-01-31 Sunbowen Lee , Shiwen Ni , Chi Wei , Shuaimin Li , Liyang Fan , Ahmadreza Argha , Hamid Alinejad-Rokny , Ruifeng Xu , Yicheng Gong , Min Yang

The delicate equilibrium between user privacy and the ability to unleash the potential of distributed data is an important concern. Federated learning, which enables the training of collaborative models without sharing of data, has emerged…

Machine Learning · Computer Science 2025-07-01 Taejin Kim , Jiarui Li , Shubhranshu Singh , Nikhil Madaan , Carlee Joe-Wong

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial…

Computer Vision and Pattern Recognition · Computer Science 2017-02-14 Alexey Kurakin , Ian Goodfellow , Samy Bengio

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

Computation and Language · Computer Science 2026-05-12 Jyotin Goel , Souvik Maji , Pratik Mazumder