English
Related papers

Related papers: Adversarial Tokenization

200 papers

Machine Learning models have been shown to be vulnerable to adversarial examples, ie. the manipulation of data by a attacker to defeat a defender's classifier at test time. We present a novel probabilistic definition of adversarial examples…

Machine Learning · Statistics 2018-01-09 Martin Gubri

Autoregressive language models (LMs) map token sequences to probabilities. The usual practice for computing the probability of any character string (e.g. English sentences) is to first transform it into a sequence of tokens that is scored…

Computation and Language · Computer Science 2023-07-03 Nadezhda Chirkova , Germán Kruszewski , Jos Rozen , Marc Dymetman

Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the…

Machine Learning · Computer Science 2018-05-09 Motoki Sato , Jun Suzuki , Hiroyuki Shindo , Yuji Matsumoto

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Computation and Language · Computer Science 2025-10-07 Jiawei Kong , Hao Fang , Xiaochen Yang , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu , Han Qiu

Passwords remain one of the most common methods for securing sensitive data in the digital age. However, weak password choices continue to pose significant risks to data security and privacy. This study aims to solve the problem by focusing…

Cryptography and Security · Computer Science 2025-06-03 Pappu Jha , Hanzla Hamid , Oluseyi Olukola , Ashim Dahal , Nick Rahimi

Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization. The expense of producing these examples during training often…

Machine Learning · Computer Science 2019-10-28 Ali Shafahi , Amin Ghiasi , Furong Huang , Tom Goldstein

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

Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the…

Computer Vision and Pattern Recognition · Computer Science 2019-08-19 Ameya Joshi , Amitangshu Mukherjee , Soumik Sarkar , Chinmay Hegde

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

Cryptography and Security · Computer Science 2023-12-15 Sicheng Zhu , Ruiyi Zhang , Bang An , Gang Wu , Joe Barrow , Zichao Wang , Furong Huang , Ani Nenkova , Tong Sun

Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust safety comes not from enumerating what is harmful, but from…

Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the…

Computation and Language · Computer Science 2023-10-05 Xianjun Yang , Xiao Wang , Qi Zhang , Linda Petzold , William Yang Wang , Xun Zhao , Dahua Lin

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…

Computation and Language · Computer Science 2024-05-21 Tom Roth , Inigo Jauregi Unanue , Alsharif Abuadbba , Massimo Piccardi

Data for deep learning should be protected for privacy preserving. Researchers have come up with the notion of learnable image encryption to satisfy the requirement. However, existing privacy preserving approaches have never considered the…

Image and Video Processing · Electrical Eng. & Systems 2019-08-01 MaungMaung AprilPyone , Warit Sirichotedumrong , Hitoshi Kiya

The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural…

Computation and Language · Computer Science 2020-06-15 Zhaoyang Wang , Hongtao Wang

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…

Machine Learning · Computer Science 2017-02-09 Sandy Huang , Nicolas Papernot , Ian Goodfellow , Yan Duan , Pieter Abbeel

Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT) and reinforcement learning from human feedback (RLHF). In…

Artificial Intelligence · Computer Science 2025-06-18 Jiahao Yu , Haozheng Luo , Jerry Yao-Chieh Hu , Wenbo Guo , Han Liu , Xinyu Xing

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…

Machine Learning · Computer Science 2021-09-23 Liping Yuan , Xiaoqing Zheng , Yi Zhou , Cho-Jui Hsieh , Kai-wei Chang

As large language models (LLMs) and generative AI become increasingly integrated into customer service and moderation applications, adversarial threats emerge from both external manipulations and internal label corruption. In this work, we…

Cryptography and Security · Computer Science 2025-08-11 Ko-Wei Chuang , Hen-Hsen Huang , Tsai-Yen Li

Building an effective adversarial attacker and elaborating on countermeasures for adversarial attacks for natural language processing (NLP) have attracted a lot of research in recent years. However, most of the existing approaches focus on…

Computation and Language · Computer Science 2020-10-20 Wenjuan Han , Liwen Zhang , Yong Jiang , Kewei Tu

Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and…

Machine Learning · Computer Science 2019-10-11 Shixian Wen , Laurent Itti