Cover Image

Cascading Adversarial Bias from Injection to Distillation in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chaudhari, Harsh, Hayes, Jamie, Jagielski, Matthew, Shumailov, Ilia, Nasr, Milad, Oprea, Alina
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
by: Chaudhari, Harsh, et al.
Published: (2026)

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
by: Chaudhari, Harsh, et al.
Published: (2024)

Buffer Overflow in Mixture of Experts
by: Hayes, Jamie, et al.
Published: (2024)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
by: Nasr, Milad, et al.
Published: (2025)

Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
by: Foerster, Hanna, et al.
Published: (2025)

Beyond Slow Signs in High-fidelity Model Extraction
by: Foerster, Hanna, et al.
Published: (2024)

Lessons from Defending Gemini Against Indirect Prompt Injections
by: Shi, Chongyang, et al.
Published: (2025)

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
by: Hayes, Jamie, et al.
Published: (2024)

Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
by: Suri, Anshuman, et al.
Published: (2025)

Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security
by: Naseh, Ali, et al.
Published: (2025)

Soft Instruction De-escalation Defense
by: Walter, Nils Philipp, et al.
Published: (2025)

Interpreting the Repeated Token Phenomenon in Large Language Models
by: Yona, Itay, et al.
Published: (2025)

R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model
by: Naseh, Ali, et al.
Published: (2025)

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

UTrace: Poisoning Forensics for Private Collaborative Learning
by: Rose, Evan, et al.
Published: (2024)

Black-Box Privacy Attacks on Shared Representations in Multitask Learning
by: Abascal, John, et al.
Published: (2025)

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
by: Foerster, Hanna, et al.
Published: (2026)

Remote Timing Attacks on Efficient Language Model Inference
by: Carlini, Nicholas, et al.
Published: (2024)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
by: Steinke, Thomas, et al.
Published: (2024)

Adversarial Inception Backdoor Attacks against Reinforcement Learning
by: Rathbun, Ethan, et al.
Published: (2024)

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

Identifying Models Behind Text-to-Image Leaderboards
by: Naseh, Ali, et al.
Published: (2026)

SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
by: Gao, Yue, et al.
Published: (2023)

Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries
by: Laws, Matthew D., et al.
Published: (2026)

Locking Machine Learning Models into Hardware
by: Clifford, Eleanor, et al.
Published: (2024)

Privacy Side Channels in Machine Learning Systems
by: Debenedetti, Edoardo, et al.
Published: (2023)

Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
by: Furukawa, Sae, et al.
Published: (2026)

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
by: Huang, Yangsibo, et al.
Published: (2025)

Exploring the limits of strong membership inference attacks on large language models
by: Hayes, Jamie, et al.
Published: (2025)

ceLLMate: Sandboxing Browser AI Agents
by: Meng, Luoxi, et al.
Published: (2025)

TMI! Finetuned Models Leak Private Information from their Pretraining Data
by: Abascal, John, et al.
Published: (2023)

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

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

SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
by: Rathbun, Ethan, et al.
Published: (2024)

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

Machine Learning Models Have a Supply Chain Problem
by: Meiklejohn, Sarah, et al.
Published: (2025)

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
by: Naseh, Ali, et al.
Published: (2025)

Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning
by: Rinberg, Roy, et al.
Published: (2025)

ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
by: Clifford, Eleanor, et al.
Published: (2022)

When Vision Fails: Text Attacks Against ViT and OCR
by: Boucher, Nicholas, et al.
Published: (2023)