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.
Adversarial Entropy Inflation Against Gumbel-Based Inference Verification
Related stories
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 Machine Learning
Jun 4
Bypassing Prompt Guards in Production with Controlled-Release Prompting
arXiv:2510. 01529v3 Announce Type: replace Abstract: Ball et al.
arXiv AI
Aug 19
The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges
The paper introduces LeakGauge, a method that appends a suffix to a model’s input to gauge the risk of context leakage before decoding. By mapping prefill token probabilities to an attack‑risk score, LeakGauge achieves high AUROC (0.944–0.996) across 11 large language models, including GLM‑5.2 and Kimi‑K3, and remains robust to language changes and different attack styles. The approach also demonstrates sensitivity to internal leakage directions and can be implemented with fewer than 0.5K additional parameters and minimal latency.
arXiv AI
Jul 9
NonTextual Target Attack
arXiv:2510. 02999v5 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses.
arXiv AI
Aug 18
Synchronized Logit Steering: Real-world Steganography
arXiv:2608. 14697v1 Announce Type: new Abstract: Steganography in large language models offers a way to embed hidden messages within natural-sounding text.
arXiv Machine Learning
Jun 30
FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks
arXiv:2606. 28962v1 Announce Type: cross Abstract: Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks.
arXiv Machine Learning
4d ago
Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification
The paper introduces a privacy‑preserving zk‑SNARK audit framework that uses adversarial‑style probes to detect logit drift between an approved large language model and a modified deployment. It offers three probe families—token‑based (black‑box), embedding‑based (gray‑box), and stress probes (partial white‑box)—allowing users to balance sensitivity, access, and cost. Experiments across LLM architectures and GPU platforms show token‑based probes achieve the highest mean sensitivity while remaining practical in a black‑box setting, with Groth16 proving times scaling modestly from 1.02 to 1.78 seconds and constant proof size.
arXiv AI
Aug 5
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels
arXiv:2608. 02995v1 Announce Type: cross Abstract: Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens.