相关论文: Adversarial Tokenization

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…

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…

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,…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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,…

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…

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…

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…

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…

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,…