paper-with-me

Papers

Adversarial Evasion Attack Efficiency against Large Language Models

2024-06-12 · João Vitorino, Eva Maia, Isabel Praça

Large Language Models (LLMs) are valuable for text classification, but their vulnerabilities must not be disregarded. They lack robustness against adversarial examples, so it is pertinent to understand the impacts of different types of perturbations, and assess if those attacks could be replicated by common users with a small amount of perturbations and a small number of queries to a deployed LLM. This work presents an analysis of the effectiveness, efficiency, and practicality of three different types of adversarial attacks against five different LLMs in a sentiment classification task. The obtained results demonstrated the very distinct impacts of the word-level and character-level attacks. The word attacks were more effective, but the character and more constrained attacks were more practical and required a reduced number of perturbations and queries. These differences need to be considered during the development of adversarial defense strategies to train more robust LLMs for intelligent text classification applications.

📄 PDF Abstract BibTeX arXiv:2406.08050

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial DefenseClassificationSentiment AnalysisSentiment Classificationtext-classificationText Classification

Similar Papers 제목 키워드 기반

Evasion Attacks Against Bayesian Predictive Models

2025-06-11 · Pablo G. Arce, Roi Naveiro, David Ríos Insua

There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against …

Omni: Automated Ensemble with Unexpected Models against Adversarial Evasion Attack

2020-11-23 · Rui Shu, Tianpei Xia, Laurie Williams, Tim Menzies

Background: Machine learning-based security detection models have become prevalent in modern malware and intrusion detection systems. However, previous studies show that such models are susceptible to adversarial evasion…

BIG-bench Machine LearningEnsemble LearningHyperparameter OptimizationIntrusion Detection

Multi-SpacePhish: Extending the Evasion-space of Adversarial Attacks against Phishing Website Detectors using Machine Learning

2022-10-24 · Ying Yuan, Giovanni Apruzzese, Mauro Conti

Existing literature on adversarial Machine Learning (ML) focuses either on showing attacks that break every ML model, or defenses that withstand most attacks. Unfortunately, little consideration is given to the actual fe…

Phishing Website Detection

Adversarial Feature Selection against Evasion Attacks

2020-05-25 · Fei Zhang, Patrick P. K. Chan, Battista Biggio, Daniel S. Yeung 외

Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion and malware detection, although their security against well-crafted attacks that aim to e…

feature selectionMalware Detection

Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples

2019-05-05 · Vikash Sehwag, Arjun Nitin Bhagoji, Liwei Song, Chawin Sitawarin 외

A large body of recent work has investigated the phenomenon of evasion attacks using adversarial examples for deep learning systems, where the addition of norm-bounded perturbations to the test inputs leads to incorrect …

Autonomous DrivingGeneral Classification