Related papers: Revisiting Character-level Adversarial Attacks for…

Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations. In this paper, we propose another type of adversarial attack that can cheat classifiers by significant…

The textual adversarial attack refers to an attack method in which the attacker adds imperceptible perturbations to the original texts by elaborate design so that the NLP (natural language processing) model produces false judgments. This…

Text classification systems have been proven vulnerable to adversarial text examples, modified versions of the original text examples that are often unnoticed by human eyes, yet can force text classification models to alter their…

Recent advances in mechanistic interpretability suggest that intermediate attention layers encode token-level hypotheses that are iteratively refined toward the final output. In this work, we exploit this property to generate adversarial…

Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial prompts. Predominant token-level optimization methods…

Adversarial examples seem to be inevitable. These specifically crafted inputs allow attackers to arbitrarily manipulate machine learning systems. Even worse, they often seem harmless to human observers. In our digital society, this poses a…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Gradient-based adversarial prompting, such as the Greedy Coordinate Gradient (GCG) algorithm, has emerged as a powerful method for jailbreaking large language models (LLMs). In this paper, we present a systematic appraisal of GCG and its…

Word-level textual adversarial attacks have demonstrated notable efficacy in misleading Natural Language Processing (NLP) models. Despite their success, the underlying reasons for their effectiveness and the fundamental characteristics of…

In light of the widespread application of Automatic Speech Recognition (ASR) systems, their security concerns have received much more attention than ever before, primarily due to the susceptibility of Deep Neural Networks. Previous studies…

We propose the first character-level white-box adversarial attack method against transformer models. The intuition of our method comes from the observation that words are split into subtokens before being fed into the transformer models and…

The success of pre-trained word embeddings has motivated its use in tasks in the biomedical domain. The BERT language model has shown remarkable results on standard performance metrics in tasks such as Named Entity Recognition (NER) and…

Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…

Recent work has demonstrated the vulnerability of modern text classifiers to universal adversarial attacks, which are input-agnostic sequences of words added to text processed by classifiers. Despite being successful, the word sequences…

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods…

We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified…

Modern language models are internally -- and mathematically -- distributions over $\it{token}$ strings rather than $\it{character}$ strings, posing numerous challenges for programmers building user applications on top of them. For example,…

The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body…

In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attackers can carefully curate input strings that mislead LLMs…