Cover Image

Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rachmil, Oren, Shapira, Avishag, Betser, Roy, Gershon, Itay, Hofman, Omer, Shabtai, Asaf, Elovici, Yuval, Vainshtein, Roman
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood
by: Betser, Roy, et al.
Published: (2025)

Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility
by: Segal, Tom, et al.
Published: (2026)

FRAME : Comprehensive Risk Assessment Framework for Adversarial Machine Learning Threats
by: Shapira, Avishag, et al.
Published: (2025)

DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs
by: Ganon, Ben, et al.
Published: (2024)

Real-World Adversarial Attacks on RF-Based Drone Detectors
by: Gazit, Omer, et al.
Published: (2025)

CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistants
by: Noah, Amit Finkman, et al.
Published: (2024)

LLMCloudHunter: Harnessing LLMs for Automated Extraction of Detection Rules from Cloud-Based CTI
by: Schwartz, Yuval, et al.
Published: (2024)

DOMBA: Double Model Balancing for Access-Controlled Language Models via Minimum-Bounded Aggregation
by: Segal, Tom, et al.
Published: (2024)

Mind the Web: The Security of Web Use Agents
by: Shapira, Avishag, et al.
Published: (2025)

RAPID: Robust APT Detection and Investigation Using Context-Aware Deep Learning
by: Amaru, Yonatan, et al.
Published: (2024)

Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack
by: Antebi, Sagiv, et al.
Published: (2025)

SoK: Cybersecurity Assessment of Humanoid Ecosystem
by: Surve, Priyanka Prakash, et al.
Published: (2025)

RuleGenie: SIEM Detection Rule Set Optimization
by: Shukla, Akansha, et al.
Published: (2025)

Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs
by: German, Eyal, et al.
Published: (2025)

MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data
by: German, Eyal, et al.
Published: (2025)

QuantAttack: Exploiting Dynamic Quantization to Attack Vision Transformers
by: Baras, Amit, et al.
Published: (2023)

Addressing Key Challenges of Adversarial Attacks and Defenses in the Tabular Domain: A Methodological Framework for Coherence and Consistency
by: Itzhakev, Yael, et al.
Published: (2024)

Identifying Memorization of Diffusion Models through $p$-Laplace Analysis: Estimators, Bounds and Applications
by: Brokman, Jonathan, et al.
Published: (2025)

LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data
by: German, Eyal, et al.
Published: (2025)

Detection of Compromised Functions in a Serverless Cloud Environment
by: Lavi, Danielle, et al.
Published: (2024)

GenKubeSec: LLM-Based Kubernetes Misconfiguration Detection, Localization, Reasoning, and Remediation
by: Malul, Ehud, et al.
Published: (2024)

A Privacy Enhancing Technique to Evade Detection by Street Video Cameras Without Using Adversarial Accessories
by: Shams, Jacob, et al.
Published: (2025)

From Tool Orchestration to Code Execution: A Study of MCP Design Choices
by: Felendler, Yuval, et al.
Published: (2026)

AgentGuardian: Learning Access Control Policies to Govern AI Agent Behavior
by: Abaev, Nadya, et al.
Published: (2026)

Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis
by: Brokman, Jonathan, et al.
Published: (2024)

SHIELD: APT Detection and Intelligent Explanation Using LLM
by: Gandhi, Parth Atulbhai, et al.
Published: (2025)

Rogue Cell: Adversarial Attack and Defense in Untrusted O-RAN Setup Exploiting the Traffic Steering xApp
by: Aizikovich, Eran, et al.
Published: (2025)

DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision Transformers
by: Yehezkel, Oryan, et al.
Published: (2024)

ImpReSS: Implicit Recommender System for Support Conversations
by: Haller, Omri, et al.
Published: (2025)

MAPS: A Multilingual Benchmark for Agent Performance and Security
by: Hofman, Omer, et al.
Published: (2025)

Whitened CLIP as a Likelihood Surrogate of Images and Captions
by: Betser, Roy, et al.
Published: (2025)

Peacock: UEFI Firmware Runtime Observability Layer for Detection and Response
by: Gorelik, Hadar Cochavi, et al.
Published: (2026)

Inference-Time Backdoors via Chat Templates: From LLM Supply Chains to Agentic System Compromise
by: Fogel, Ariel, et al.
Published: (2026)

When Scanners Lie: Evaluator Instability in LLM Red-Teaming
by: Erez, Lidor, et al.
Published: (2026)

Rule-ATT&CK Mapper (RAM): Mapping SIEM Rules to TTPs Using LLMs
by: Wudali, Prasanna N., et al.
Published: (2025)

UEFI Memory Forensics: A Framework for UEFI Threat Analysis
by: Segal, Kalanit Suzan, et al.
Published: (2025)

Towards an End-to-End (E2E) Adversarial Learning and Application in the Physical World
by: Biton, Dudi, et al.
Published: (2025)

GPT in Sheep's Clothing: The Risk of Customized GPTs
by: Antebi, Sagiv, et al.
Published: (2024)

KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and Runtime Logs Analysis
by: Cohen, Omri Sgan, et al.
Published: (2025)

AgenTRIM: Tool Risk Mitigation for Agentic AI
by: Betser, Roy, et al.
Published: (2026)