Related papers: HQA-Attack: Toward High Quality Black-Box Hard-Lab…
Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods. Current…
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but its openness introduces vulnerabilities that can be exploited by poisoning attacks. Existing poisoning methods for RAG…
Researchers have repeatedly shown that it is possible to craft adversarial attacks on deep classifiers (small perturbations that significantly change the class label), even in the "black-box" setting where one only has query access to the…
Over the past few years, various word-level textual attack approaches have been proposed to reveal the vulnerability of deep neural networks used in natural language processing. Typically, these approaches involve an important optimization…
Traditional decision-based black-box adversarial attacks on image classifiers aim to generate adversarial examples by slightly modifying input images while keeping the number of queries low, where each query involves sending an input to the…
Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…
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…
Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…
CNN-based face recognition models have brought remarkable performance improvement, but they are vulnerable to adversarial perturbations. Recent studies have shown that adversaries can fool the models even if they can only access the models'…
Numerous works study black-box attacks on image classifiers. However, these works make different assumptions on the adversary's knowledge and current literature lacks a cohesive organization centered around the threat model. To systematize…
Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities.…
We introduce the Text Classification Attack Benchmark (TCAB), a dataset for analyzing, understanding, detecting, and labeling adversarial attacks against text classifiers. TCAB includes 1.5 million attack instances, generated by twelve…
Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…
Deep learning models are susceptible to adversarial examples that have imperceptible perturbations in the original input, resulting in adversarial attacks against these models. Analysis of these attacks on the state of the art transformers…
Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models. Most of these attacks need to handle a vast optimization space and require a large number of queries,…
This paper concerns corpus poisoning attacks in dense information retrieval, where an adversary attempts to compromise the ranking performance of a search algorithm by injecting a small number of maliciously generated documents into the…
We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization~(BO) to specifically…
Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the training efficiency of Large Language Models (LLMs) by updating neural network layers…
Query-based black-box attacks have emerged as a significant threat to machine learning systems, where adversaries can manipulate the input queries to generate adversarial examples that can cause misclassification of the model. To counter…
Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception,…