Attacking machine learning with adversarial examples

Position: Adversarial ML for LLMs Is Not Making Any Progress

arXiv:2502. 02260v2 Announce Type: replace Abstract: In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings.

Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets

Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision data that can behave like backdoor-like triggers without being maliciously inserted.

Adversarial attacks on neural network policies

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

arXiv:2406. 10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization.

Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets

arXiv:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.

Statistically Undetectable Backdoors in Deep Neural Networks

arXiv:2607. 09532v1 Announce Type: new Abstract: We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks.

A unifying Bayesian framework for adversarial robustness

arXiv:2510. 09288v2 Announce Type: replace-cross Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge.

Robust adversarial inputs

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.

Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets

arXiv:2607. 05516v2 Announce Type: replace-cross Abstract: Model-specific adversarial attacks have been extensively studied.

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

arXiv:2503. 01734v3 Announce Type: replace-cross Abstract: Attacks on machine learning models have been extensively studied through stateless optimization.

SoK: Colluding Adversaries in Machine Learning Pipelines

arXiv:2606. 10091v1 Announce Type: cross Abstract: Machine learning (ML) models are susceptible to various security, privacy, and fairness risks.