Cover Image

Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Glukhov, David, Han, Ziwen, Shumailov, Ilia, Papyan, Vardan, Papernot, Nicolas
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
by: Thudi, Anvith, et al.
Published: (2023)

Architectural Neural Backdoors from First Principles
by: Langford, Harry, et al.
Published: (2024)

LeakDojo: Decoding the Leakage Threats of RAG Systems
by: Zhang, Maosen, et al.
Published: (2026)

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
by: Shumailov, Ilia, et al.
Published: (2024)

The Curse of Recursion: Training on Generated Data Makes Models Forget
by: Shumailov, Ilia, et al.
Published: (2023)

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
by: Rabanser, Stephan, et al.
Published: (2025)

ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI
by: Tong, Haibo, et al.
Published: (2026)

Towards Understanding Unsafe Video Generation
by: Pang, Yan, et al.
Published: (2024)

Preserving Decision Sovereignty in Military AI: A Trade-Secret-Safe Architectural Framework for Model Replaceability, Human Authority, and State Control
by: Wei, Peng, et al.
Published: (2026)

Global Challenge for Safe and Secure LLMs Track 1
by: Jia, Xiaojun, et al.
Published: (2024)

Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation
by: Küchler, Nicolas, et al.
Published: (2025)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
by: Li, Na, et al.
Published: (2025)

Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks
by: Dahiya, Pranav, et al.
Published: (2023)

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

Black-Box Access is Insufficient for Rigorous AI Audits
by: Casper, Stephen, et al.
Published: (2024)

AI Safety vs. AI Security: Demystifying the Distinction and Boundaries
by: Lin, Zhiqiang, et al.
Published: (2025)

AI Risk-Management Standards Profile for General-Purpose AI (GPAI) and Foundation Models
by: Barrett, Anthony M., et al.
Published: (2025)

Beyond Labeling Oracles: What does it mean to steal ML models?
by: Shafran, Avital, et al.
Published: (2023)

Private, Verifiable, and Auditable AI Systems
by: South, Tobin
Published: (2025)

Frontier AI's Impact on the Cybersecurity Landscape
by: Potter, Yujin, et al.
Published: (2025)

Red Teaming AI Red Teaming
by: Majumdar, Subhabrata, et al.
Published: (2025)

AI Propaganda factories with language models
by: Olejnik, Lukasz
Published: (2025)

Accelerating AI Development with Cyber Arenas
by: Cashman, William, et al.
Published: (2025)

AI-Driven Cyber Threat Intelligence Automation
by: Shah, Shrit, et al.
Published: (2024)

Securing the Future of GenAI: Policy and Technology
by: Christodorescu, Mihai, et al.
Published: (2024)

The Pitfalls of "Security by Obscurity" And What They Mean for Transparent AI
by: Hall, Peter, et al.
Published: (2025)

Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities
by: Cattell, Sven, et al.
Published: (2024)

Interplay of ISMS and AIMS in context of the EU AI Act
by: Pötsch, Jordan
Published: (2024)

The End Of Universal Lifelong Identifiers: Identity Systems For The AI Era
by: Palakodety, Shriphani
Published: (2025)

Enabling External Scrutiny of AI Systems with Privacy-Enhancing Technologies
by: Beers, Kendrea, et al.
Published: (2025)

RedTeamLLM: an Agentic AI framework for offensive security
by: Challita, Brian, et al.
Published: (2025)

Governable AI: Provable Safety Under Extreme Threat Models
by: Wang, Donglin, et al.
Published: (2025)

Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
by: Lin, Justin W., et al.
Published: (2025)

Naming is framing: How cybersecurity's language problems are repeating in AI governance
by: Potter, Lianne
Published: (2025)

The Impact of AI on the Cyber Offense-Defense Balance and the Character of Cyber Conflict
by: Lohn, Andrew J.
Published: (2025)

Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses
by: Qayyum, Adnan, et al.
Published: (2022)

Is Your AI Truly Yours? Leveraging Blockchain for Copyrights, Provenance, and Lineage
by: Wang, Qin, et al.
Published: (2024)

Clear, Compelling Arguments: Rethinking the Foundations of Frontier AI Safety Cases
by: Feakins, Shaun, et al.
Published: (2026)

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

Can AI Models be Jailbroken to Phish Elderly Victims? An End-to-End Evaluation
by: Heiding, Fred, et al.
Published: (2025)