arXiv Machine Learning
Margin-Drop Coordinates for Cross-Budget Robustness Evaluation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 10
Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers
arXiv:2608. 06674v1 Announce Type: cross Abstract: Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded in many safety-critical systems.
arXiv AI
Jun 3
Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs
arXiv:2606. 03879v1 Announce Type: cross Abstract: As foundation models scale toward fusing more heterogeneous visual streams, understanding how diverse encoders interact under joint training becomes a prerequisite for principled design.
arXiv Machine Learning
Sep 16
The Scissors Effect: When Resize-Based Input Diversity Helps or Hurts Transfer Attacks
arXiv:2606.22516v2 Announce Type: replace Abstract: Input Diversity (DI), a random resize and pad applied at each attack iteration, is a near-default ingredient of transfer-based attacks, widely assu...
arXiv AI
Aug 7
Supervised Learning Has a Geometric Blind Spot
arXiv:2604. 21395v3 Announce Type: replace-cross Abstract: Ordinary supervised training minimises the task loss and then stops.
arXiv AI
Jun 18
Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restoration
arXiv:2505. 03646v5 Announce Type: replace-cross Abstract: Adversarial robustness of deep autoencoders (AEs) has received less attention than that of discriminative models, although their compressed latent representations induce ill-conditioned mappings that can amplify small input perturbations and destabilize reconstructions.
arXiv AI
Aug 11
Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks
arXiv:2607. 26574v2 Announce Type: replace-cross Abstract: Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet a guard judges an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a classical language, code, or text rendered inside an image slips past a guard that would block it in plain language - the decode gap.