Image de couverture de livre

Evading Data Contamination Detection for Language Models is (too) Easy

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dekoninck, Jasper, Müller, Mark Niklas, Baader, Maximilian, Fischer, Marc, Vechev, Martin
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence Computation and Language Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AutoBaxBuilder: Bootstrapping Code Security Benchmarking
par: von Arx, Tobias, et autres
Publié: (2025)

Ward: Provable RAG Dataset Inference via LLM Watermarks
par: Jovanović, Nikola, et autres
Publié: (2024)

BaxBench: Can LLMs Generate Correct and Secure Backends?
par: Vero, Mark, et autres
Publié: (2025)

Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
par: Dekoninck, Jasper, et autres
Publié: (2024)

CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization
par: Das, Debeshee, et autres
Publié: (2025)

Time Travel in LLMs: Tracing Data Contamination in Large Language Models
par: Golchin, Shahriar, et autres
Publié: (2023)

ConStat: Performance-Based Contamination Detection in Large Language Models
par: Dekoninck, Jasper, et autres
Publié: (2024)

Watermark Stealing in Large Language Models
par: Jovanović, Nikola, et autres
Publié: (2024)

Large Language Models are Advanced Anonymizers
par: Staab, Robin, et autres
Publié: (2024)

Watermarking Diffusion Language Models
par: Gloaguen, Thibaud, et autres
Publié: (2025)

Discovering Spoofing Attempts on Language Model Watermarks
par: Gloaguen, Thibaud, et autres
Publié: (2024)

SPEAR:Exact Gradient Inversion of Batches in Federated Learning
par: Dimitrov, Dimitar I., et autres
Publié: (2024)

Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems
par: Berezin, Sergey, et autres
Publié: (2024)

Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
par: Dong, Yihong, et autres
Publié: (2024)

Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
par: Gloaguen, Thibaud, et autres
Publié: (2025)

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation
par: De Muri, Giovanni, et autres
Publié: (2025)

Detecting Training Data of Large Language Models via Expectation Maximization
par: Kim, Gyuwan, et autres
Publié: (2024)

Exploiting LLM Quantization
par: Egashira, Kazuki, et autres
Publié: (2024)

Fewer Weights, More Problems: A Practical Attack on LLM Pruning
par: Egashira, Kazuki, et autres
Publié: (2025)

Mind the Gap: A Practical Attack on GGUF Quantization
par: Egashira, Kazuki, et autres
Publié: (2025)

BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs
par: Petrov, Ivo, et autres
Publié: (2025)

On The Fragility of Benchmark Contamination Detection in Reasoning Models
par: Wang, Han, et autres
Publié: (2025)

Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models
par: Russinovich, Mark, et autres
Publié: (2025)

AuthorMist: Evading AI Text Detectors with Reinforcement Learning
par: David, Isaac, et autres
Publié: (2025)

AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports
par: Lange, Lukas, et autres
Publié: (2024)

A Unified Framework for LLM Watermarks
par: Gloaguen, Thibaud, et autres
Publié: (2026)

Instruction Tuning for Secure Code Generation
par: He, Jingxuan, et autres
Publié: (2024)

Memories Retrieved from Many Paths: A Multi-Prefix Framework for Robust Detection of Training Data Leakage in Large Language Models
par: Dang, Trung Cuong, et autres
Publié: (2025)

Detection Made Easy: Potentials of Large Language Models for Solidity Vulnerabilities
par: Alam, Md Tauseef, et autres
Publié: (2024)

Large Language Models for Code: Security Hardening and Adversarial Testing
par: He, Jingxuan, et autres
Publié: (2023)

Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
par: Gloaguen, Thibaud, et autres
Publié: (2026)

Extracting Training Data from Diffusion Language Models via Infilling
par: Wang, Yihan, et autres
Publié: (2026)

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
par: Hua, Peichun, et autres
Publié: (2025)

A Unified Approach to Routing and Cascading for LLMs
par: Dekoninck, Jasper, et autres
Publié: (2024)

Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)
par: Abadi, Aydin, et autres
Publié: (2024)

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
par: Hu, Xiaomeng, et autres
Publié: (2024)

Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
par: Xu, Yijie, et autres
Publié: (2025)

Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models
par: Bai, Yang, et autres
Publié: (2024)

Adaptive Generation of Bias-Eliciting Questions for LLMs
par: Staab, Robin, et autres
Publié: (2025)

KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection
par: Li, Yuexin, et autres
Publié: (2024)