Cover Image

GAVEL: Towards Rule-Based Safety Through Activation Monitoring

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rozenfeld, Shir, Pankajakshan, Rahul, Zloczower, Itay, Lenga, Eyal, Gressel, Gilad, Mirsky, Yisroel
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries
by: Zloczower, Itay, et al.
Published: (2026)

Love, Lies, and Language Models: Investigating AI's Role in Romance-Baiting Scams
by: Gressel, Gilad, et al.
Published: (2025)

Who Owns This Agent? Tracing AI Agents Back to Their Owners
by: Chocron, Ruben, et al.
Published: (2026)

Are You Human? An Adversarial Benchmark to Expose LLMs
by: Gressel, Gilad, et al.
Published: (2024)

Mapping LLM Security Landscapes: A Comprehensive Stakeholder Risk Assessment Proposal
by: Pankajakshan, Rahul, et al.
Published: (2024)

PEAS: A Strategy for Crafting Transferable Adversarial Examples
by: Avraham, Bar, et al.
Published: (2024)

Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks
by: Bokobza, Roey, et al.
Published: (2024)

ProxyPrints: From Database Breach to Spoof, A Plug-and-Play Defense for Biometric Systems
by: Hacmon, Yaniv, et al.
Published: (2025)

The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks
by: Ayzenshteyn, Daniel, et al.
Published: (2024)

Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias
by: Bernstein, Shir, et al.
Published: (2025)

What Was Your Prompt? A Remote Keylogging Attack on AI Assistants
by: Weiss, Roy, et al.
Published: (2024)

Efficient Model Extraction via Boundary Sampling
by: Dor, Maor Biton, et al.
Published: (2024)

ASRJam: Human-Friendly AI Speech Jamming to Prevent Automated Phone Scams
by: Grabovski, Freddie, et al.
Published: (2025)

Transpose Attack: Stealing Datasets with Bidirectional Training
by: Amit, Guy, et al.
Published: (2023)

Transferability Ranking of Adversarial Examples
by: Levy, Mosh, et al.
Published: (2022)

Robust Safety Monitoring of Language Models via Activation Watermarking
by: Aremu, Toluwani, et al.
Published: (2026)

Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models
by: Hadad, Eyal, et al.
Published: (2026)

Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem
by: Lin, Shuyi, et al.
Published: (2025)

Differentially Private Iterative Screening Rules for Linear Regression
by: Khanna, Amol, et al.
Published: (2025)

Uncertainty-Aware Hardware Trojan Detection Using Multimodal Deep Learning
by: Vishwakarma, Rahul, et al.
Published: (2024)

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search
by: Luo, Zeren, et al.
Published: (2025)

Smooth Sensitivity for Learning Differentially-Private yet Accurate Rule Lists
by: Ly, Timothée, et al.
Published: (2024)

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
by: Panda, Ashwinee, et al.
Published: (2022)

FAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigations
by: Shuster, Shaun, et al.
Published: (2025)

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
by: Lai, Zhenglin, et al.
Published: (2025)

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
by: Huang, Tiansheng, et al.
Published: (2025)

Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learning
by: Diana, Francesco, et al.
Published: (2025)

Eclectic Rule Extraction for Explainability of Deep Neural Network based Intrusion Detection Systems
by: Ables, Jesse, et al.
Published: (2024)

Saffron-1: Safety Inference Scaling
by: Qiu, Ruizhong, et al.
Published: (2025)

Quantized Delta Weight Is Safety Keeper
by: Liu, Yule, et al.
Published: (2024)

Towards Family-Grouped Hierarchical Federated Learning on Sub-5KB Models: A Feasibility Study of Privacy-Preserving ECG Monitoring for Ultra-Resource-Constrained Wearables
by: Wu, Hangyu
Published: (2026)

Reliable Weak-to-Strong Monitoring of LLM Agents
by: Kale, Neil, et al.
Published: (2025)

Stealing User Prompts from Mixture of Experts
by: Yona, Itay, et al.
Published: (2024)

In-Context Representation Hijacking
by: Yona, Itay, et al.
Published: (2025)

Privacy-Preserving Data Sharing in Agriculture: Enforcing Policy Rules for Secure and Confidential Data Synthesis
by: Kotal, Anantaa, et al.
Published: (2023)

Self-Mined Hardness for Safety Fine-Tuning
by: Gupta, Prakhar, et al.
Published: (2026)

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
by: Kutasov, Jonathan, et al.
Published: (2025)

Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
by: Wang, Xunguang, et al.
Published: (2026)

Why Safety Probes Catch Liars But Miss Fanatics
by: Haralambiev, Kristiyan
Published: (2026)

Understanding the Effects of Safety Unalignment on Large Language Models
by: Halloran, John T.
Published: (2026)