arXiv Machine Learning September 23, 2026 By Akanksha Raghapur, Mark Stamp

On the Effect of Bit-Level Parameter Perturbations in Machine Learning and Deep Learning Models

Read the original on arXiv Machine Learning →

The paper studies how small, targeted changes to model parameters affect classical machine learning models (HMM and SVM) versus deep learning models (MLP and LSTM). Using the Drebin Android malware dataset, it finds that classical models are brittle, with a few parameter changes dramatically altering behavior, and have limited steganographic capacity. In contrast, neural networks are parameter‑redundant, allowing many parameters to be altered with minimal impact, thus supporting higher steganographic capacity.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 9

Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs

arXiv:2606. 09411v1 Announce Type: cross Abstract: Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs.

By Charles Westphal, Timothy Douglas, Keivan Navaie, Tiago Pimentel, Fernando E. Rosas

llms fine-tuning benchmarks

arXiv AI

Jul 20

Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models

arXiv:2601. 22818v2 Announce Type: replace-cross Abstract: Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels.

By Charles Westphal, Keivan Navaie, Fernando E. Rosas

llms rag fine-tuning safety

arXiv AI

Jul 23

Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection

arXiv:2607. 20003v1 Announce Type: cross Abstract: An increase in advanced Android malware requires the use of deep learning models, which can run on Android devices.

By Shrinidhi Sridhar, Vikas K. Malviya

efficiency

arXiv AI

Jun 24

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.

By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud

llms benchmarks safety

arXiv AI

Jul 23

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.

By Yuxi Li, Zhibo Zhang, Kailong Wang, Xingshuo Han, Ling Shi, Haoyu Wang

llms fine-tuning efficiency multimodal benchmarks

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.

By Chethan Krishnamurthy Ramanaik, Arjun Roy, Tobias Callies, Eirini Ntoutsi

multimodal safety

One email a morning, machine-written

Related stories

Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs

Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models

Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restoration