English
Related papers

Related papers: Adversarial Tokenization

200 papers

Machine Learning (ML) models are applied in a variety of tasks such as network intrusion detection or Malware classification. Yet, these models are vulnerable to a class of malicious inputs known as adversarial examples. These are slightly…

Cryptography and Security · Computer Science 2017-10-18 Kathrin Grosse , Praveen Manoharan , Nicolas Papernot , Michael Backes , Patrick McDaniel

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same…

Computation and Language · Computer Science 2024-07-08 Xinglin Li , Xianwen He , Yao Li , Minhao Cheng

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Cryptography and Security · Computer Science 2025-07-15 Joshua Kazdan , Abhay Puri , Rylan Schaeffer , Lisa Yu , Chris Cundy , Jason Stanley , Sanmi Koyejo , Krishnamurthy Dvijotham

Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these attacks are applied to pre-trained large language models (LLMs), they encounter significant…

Cryptography and Security · Computer Science 2026-05-26 Meng Tong , Yuntao Du , Kejiang Chen , Weiming Zhang , Ninghui Li

An adversarial example is an input transformed by small perturbations that machine learning models consistently misclassify. While there are a number of methods proposed to generate adversarial examples for text data, it is not trivial to…

Computation and Language · Computer Science 2020-06-02 Ying Xu , Xu Zhong , Antonio Jose Jimeno Yepes , Jey Han Lau

Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms…

Machine Learning · Statistics 2018-02-14 Andrea Paudice , Luis Muñoz-González , Andras Gyorgy , Emil C. Lupu

It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely…

Machine Learning · Computer Science 2024-02-22 Jonas Geiping , Alex Stein , Manli Shu , Khalid Saifullah , Yuxin Wen , Tom Goldstein

Large language models (LLMs) have achieved remarkable performance across diverse natural language processing tasks, yet their vulnerability to character-level adversarial manipulations presents significant security challenges for real-world…

Cryptography and Security · Computer Science 2025-11-27 Ephraiem Sarabamoun

Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at…

Machine Learning · Computer Science 2026-02-17 Sam Dauncey , Roger Wattenhofer

Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking…

Machine Learning · Computer Science 2024-12-06 Jason Vega , Junsheng Huang , Gaokai Zhang , Hangoo Kang , Minjia Zhang , Gagandeep Singh

The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks. We cast the spotlight on the underexplored task of Natural Language Inference (NLI), since…

Computation and Language · Computer Science 2025-08-04 Alexandros Koulakos , Maria Lymperaiou , Giorgos Filandrianos , Giorgos Stamou

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…

Machine Learning · Computer Science 2021-06-22 Liam Fowl , Micah Goldblum , Ping-yeh Chiang , Jonas Geiping , Wojtek Czaja , Tom Goldstein

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

Machine Learning · Computer Science 2024-11-01 Yichuan Mo , Yuji Wang , Zeming Wei , Yisen Wang

While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM input space is discrete, which precludes gradient-based…

Machine Learning · Computer Science 2025-09-22 Zhengxing Li , Guangmingmei Yang , Jayaram Raghuram , David J. Miller , George Kesidis

Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However,…

Computation and Language · Computer Science 2023-05-26 Salijona Dyrmishi , Salah Ghamizi , Maxime Cordy

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Cryptography and Security · Computer Science 2026-01-28 Yangyang Guo , Ziwei Xu , Si Liu , Zhiming Zheng , Mohan Kankanhalli

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Machine Learning · Computer Science 2025-10-08 Zizhao Wang , Dingcheng Li , Vaishakh Keshava , Phillip Wallis , Ananth Balashankar , Peter Stone , Lukas Rutishauser

In this work, we make two contributions towards understanding of in-context learning of linear models by transformers. First, we investigate the adversarial robustness of in-context learning in transformers to hijacking attacks -- a type of…

Machine Learning · Computer Science 2025-08-07 Usman Anwar , Johannes Von Oswald , Louis Kirsch , David Krueger , Spencer Frei

State-of-the-art attacks on NLP models lack a shared definition of a what constitutes a successful attack. We distill ideas from past work into a unified framework: a successful natural language adversarial example is a perturbation that…

Computation and Language · Computer Science 2021-12-23 John X. Morris , Eli Lifland , Jack Lanchantin , Yangfeng Ji , Yanjun Qi

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Machine Learning · Computer Science 2025-01-22 Qizhang Li , Xiaochen Yang , Wangmeng Zuo , Yiwen Guo