Cover Image

Defeating Prompt Injections by Design

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Debenedetti, Edoardo, Shumailov, Ilia, Fan, Tianqi, Hayes, Jamie, Carlini, Nicholas, Fabian, Daniel, Kern, Christoph, Shi, Chongyang, Terzis, Andreas, Tramèr, Florian
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Evading Black-box Classifiers Without Breaking Eggs
by: Debenedetti, Edoardo, et al.
Published: (2023)

Stealing User Prompts from Mixture of Experts
by: Yona, Itay, 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)

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
by: Carlini, Nicholas, et al.
Published: (2025)

Adversarial Search Engine Optimization for Large Language Models
by: Nestaas, Fredrik, et al.
Published: (2024)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
by: Debenedetti, Edoardo, et al.
Published: (2024)

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

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

Design Patterns for Securing LLM Agents against Prompt Injections
by: Beurer-Kellner, Luca, et al.
Published: (2025)

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

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

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

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
by: Tramèr, Florian, et al.
Published: (2022)

Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
by: Hönig, Robert, et al.
Published: (2024)

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

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

Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
by: Rando, Javier, et al.
Published: (2025)

Poisoning Web-Scale Training Datasets is Practical
by: Carlini, Nicholas, et al.
Published: (2023)

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
by: Vero, Mark, et al.
Published: (2026)

Query-Based Adversarial Prompt Generation
by: Hayase, Jonathan, et al.
Published: (2024)

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

Fixing 7,400 Bugs for 1$: Cheap Crash-Site Program Repair
by: Zheng, Han, et al.
Published: (2025)

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

Defending Against Prompt Injection With a Few DefensiveTokens
by: Chen, Sizhe, et al.
Published: (2025)

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

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
by: He, Yu, et al.
Published: (2026)

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

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

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

Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense
by: Zhang, Jie, et al.
Published: (2024)

Large-scale online deanonymization with LLMs
by: Lermen, Simon, et al.
Published: (2026)

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

On Defeating Graph Analysis of Anonymous Transactions
by: Egger, Christoph, et al.
Published: (2024)

Kraken: Higher-order EM Side-Channel Attacks on DNNs in Near and Far Field
by: Horvath, Peter, et al.
Published: (2026)

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
by: Feng, Shanglun, et al.
Published: (2024)

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

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

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

Persistent Pre-Training Poisoning of LLMs
by: Zhang, Yiming, et al.
Published: (2024)

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
by: Chao, Patrick, et al.
Published: (2024)