arXiv AI June 18, 2026 By Chethan Krishnamurthy Ramanaik, Arjun Roy, Tobias Callies, Eirini Ntoutsi

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

1d ago

Fast Test-Time Refinement for Robust Learned Image Compression

arXiv:2608. 15113v1 Announce Type: cross Abstract: Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings.

By Jiaming Liang, Chi-Man Pun, Weisi Lin

safety

arXiv Machine Learning

Aug 4

DeepDefense: Robust Learning via Layer-Wise Gradient-Feature Alignment

arXiv:2511. 13749v2 Announce Type: replace Abstract: Deep neural networks are known to be vulnerable to adversarial perturbations, which are small, carefully crafted inputs that lead to incorrect predictions.

By Ci Lin, Tet Yeap, Iluju Kiringa

safety

Hugging Face Trending Papers

Jun 2

Investigating Adversarial Robustness of Multi-modal Large Language Models

Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.

llms rag fine-tuning multimodal safety

arXiv AI

Jun 29

Improving Adversarial Robustness via Activation Amplification and Attenuation

arXiv:2606. 27784v1 Announce Type: cross Abstract: The existence of adversarial attacks is often attributed to the presence of non-robust features in neural networks.

By Ta\"iga Gon\c{c}alves, Yongsong Huang, Tomo Miyazaki, Shinichiro Omachi

efficiency safety

arXiv AI

Jun 6

Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition

arXiv:2606. 05678v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems have become widely used for multilingual speech-to-text transcription.

By Yifan Liao, Zongmin Zhang, Zhen Sun, Yuhui Sun, Xinhu Zheng, Xinlei He

multimodal benchmarks safety

arXiv AI

Jun 15

Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning

arXiv:2606. 14078v1 Announce Type: cross Abstract: Existing studies reveal that current backdoor defenses exhibit limited robustness and often fail against specific types of attacks.

By Zhenqian Zhu, Yamin Hu, Yujiang Liu, Luping Wei, Wenbo Hou, Bin Li, Haodong Li, Wenjian Luo

multimodal safety

Related stories

Fast Test-Time Refinement for Robust Learned Image Compression

DeepDefense: Robust Learning via Layer-Wise Gradient-Feature Alignment

Investigating Adversarial Robustness of Multi-modal Large Language Models

Improving Adversarial Robustness via Activation Amplification and Attenuation

Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition

Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning