Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
Recent work has proposed neural network pruning techniques to reduce the size of a network while preserving robustness against adversarial examples, i.e., well-crafted inputs inducing a...
AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using different experimental...
Buffer-free Class-Incremental Learning with Out-of-Distribution Detection
Class-incremental learning (CIL) poses significant challenges in open-world scenarios, where models must not only learn new classes over time without forgetting previous ones but also handle...
LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback
Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt...
Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectors
Machine-learning phishing webpage detectors (ML-PWD) have been shown to suffer from adversarial manipulations of the HTML code of the input webpage. Nevertheless, the attacks recently proposed...
Evaluating the Evaluators: Trust in Adversarial Robustness Tests
Despite significant progress in designing powerful adversarial evasion attacks for robustness verification, the evaluation of these methods often remains inconsistent and unreliable. Many...
Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training
Deep learning models undergo a significant increase in the number of parameters they possess, leading to the execution of a larger number of operations during inference. This expansion...
ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches
Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding, and...
Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints
Evaluating adversarial robustness amounts to finding the minimum perturbation needed to have an input sample misclassified. The inherent complexity of the underlying optimization requires current...
HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks
Gradient-based attacks are a primary tool to evaluate robustness of machine-learning models. However, many attacks tend to provide overly-optimistic evaluations as they use fixed loss functions,...
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples
Evaluating robustness of machine-learning models to adversarial examples is a challenging problem. Many defenses have been shown to provide a false sense of robustness by causing gradient-based...
Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference
Adversarial reprogramming allows repurposing a machine-learning model to perform a different task. For example, a model trained to recognize animals can be reprogrammed to recognize digits by...
Explaining Machine Learning DGA Detectors from DNS Traffic Data
One of the most common causes of lack of continuity of online systems stems from a widely popular Cyber Attack known as Distributed Denial of Service (DDoS), in which a network of infected devices...
Robust Machine Learning for Malware Detection over Time
The presence and persistence of Android malware is an on-going threat that plagues this information era, and machine learning technologies are now extensively used to deploy more effective...
Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks
Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transferability has been...
Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
Although ImageNet was initially proposed as a dataset for performance benchmarking in the domain of computer vision, it also enabled a variety of other research efforts. Adversarial machine...
Stateful Detection of Adversarial Reprogramming
Adversarial reprogramming allows stealing computational resources by repurposing machine learning models to perform a different task chosen by the attacker. For example, a model trained to...
secml: A Python Library for Secure and Explainable Machine Learning
We present \texttt{secml}, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion...