arXiv AI
Adversarial Entropy Inflation Against Gumbel-Based Inference Verification
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 5
Steering Vectors are an Adversarial Attack Surface
arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.
arXiv AI
Jun 9
Steganography Without Modification: Hidden Communication via LLM Seeds
arXiv:2606. 09135v1 Announce Type: cross Abstract: We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions.
arXiv Machine Learning
Jun 30
High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models
arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.
arXiv Computation and Language
Aug 27
Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips
The paper introduces the Groundhog Bit-Flip Attack (GBFA), a novel denial-of-service attack targeting Mixture-of-Experts (MoE) large language models (LLMs). By flipping specific routing-layer bits that activate certain experts, GBFA can cause models to generate excessively long outputs—up to a 5912% increase in token usage—while largely preserving semantic content. The attack requires deactivating fewer than four experts on average across four real-world MoE-based LLMs, exposing a significant robustness vulnerability in these architectures.
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.
arXiv AI
Oct 9
Speedbumps: Rejection Attacks on Speculative Decoding
Speedbumps: Rejection Attacks on Speculative Decoding explores how Speculative Rejection Attacks (SRAs) can degrade the efficiency of speculative decoding by causing draft and target models to disagree more often, leading to more target-model forward passes per token. The authors introduce two attacks—Speedbump-P and Speedbump-D—that append adversarial suffixes to attacker-controlled content, optimizing the expected length of the accepted speculative prefix. In some scenarios, these attacks slow inference below autoregressive decoding, reduce output quality, yet remain effective under sampling and transfer across drafters or target models sharing a drafter.