Cover Image

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chaudhari, Harsh, Severi, Giorgio, Abascal, John, Suri, Anshuman, Jagielski, Matthew, Choquette-Choo, Christopher A., Nasr, Milad, Nita-Rotaru, Cristina, Oprea, Alina
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Cascading Adversarial Bias from Injection to Distillation in Language Models
by: Chaudhari, Harsh, et al.
Published: (2025)

DROP: Poison Dilution via Knowledge Distillation for Federated Learning
by: Syros, Georgios, et al.
Published: (2025)

SAGA: A Security Architecture for Governing AI Agentic Systems
by: Syros, Georgios, et al.
Published: (2025)

Backdoor Attacks in Peer-to-Peer Federated Learning
by: Syros, Georgios, et al.
Published: (2023)

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

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

Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
by: Chaudhari, Harsh, et al.
Published: (2023)

Auditing Private Prediction
by: Chadha, Karan, et al.
Published: (2024)

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

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

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

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

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

APWA: A Distributed Architecture for Parallelizable Agentic Workflows
by: Rose, Evan, et al.
Published: (2026)

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

LLMs unlock new paths to monetizing exploits
by: Carlini, Nicholas, et al.
Published: (2025)

User Inference Attacks on Large Language Models
by: Kandpal, Nikhil, et al.
Published: (2023)

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

Toward a Principled Framework for Agent Safety Measurement
by: Lin, Shuyi, et al.
Published: (2026)

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
by: Syros, Georgios, et al.
Published: (2026)

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

MAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security
by: Avizheh, Sepideh, et al.
Published: (2026)

Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
by: Carranza, Aldo Gael, et al.
Published: (2023)

ACE: A Security Architecture for LLM-Integrated App Systems
by: Li, Evan, et al.
Published: (2025)

Measuring memorization in language models via probabilistic extraction
by: Hayes, Jamie, et al.
Published: (2024)

Privacy Auditing of Large Language Models
by: Panda, Ashwinee, et al.
Published: (2025)

Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
by: Rathbun, Ethan, et al.
Published: (2026)

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

The Matrix Reloaded: A Mechanized Formal Analysis of the Matrix Cryptographic Suite
by: Ginesin, Jacob, et al.
Published: (2024)

Are aligned neural networks adversarially aligned?
by: Carlini, Nicholas, et al.
Published: (2023)

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
by: Borkar, Jaydeep, et al.
Published: (2025)

Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors
by: Peng, Yuefeng, et al.
Published: (2024)

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

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

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

Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models
by: Clop, Cody, et al.
Published: (2024)

Cross-Service Token: Finding Attacks in 5G Core Networks
by: Chen, Anqi, et al.
Published: (2025)

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
by: Liu, Ken Ziyu, et al.
Published: (2025)

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