v1v2 (latest)

Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding

International Conference on Computational Linguistics (COLING), 2024

5 September 2024

Cheng Wang

Yiwei Wang

Bryan Hooi

Yujun Cai

Nanyun Peng

Kai-Wei Chang

ArXiv (abs)PDF HTML

Papers citing "Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding"

29 / 29 papers shown

Title
False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize Cheng Wang Zeming Wei Qin Liu Muhao Chen AAML 176 1 0 04 Sep 2025
SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Kaiyuan Zhang Siyuan Cheng Hanxi Guo Yuetian Chen Zian Su ... Yuntao Du Charles Fleming Jayanth Srinivasa Xiangyu Zhang Ninghui Li AAML 364 6 0 12 Jun 2025
Exploring the limits of strong membership inference attacks on large language models Jamie Hayes Ilia Shumailov Christopher A. Choquette-Choo Matthew Jagielski G. Kaissis ... Matthieu Meeus Yves-Alexandre de Montjoye Franziska Boenisch Adam Dziedzic A. Feder Cooper 324 10 0 24 May 2025
On Membership Inference Attacks in Knowledge Distillation Ziyao Cui Minxing Zhang Jian Pei 245 2 0 17 May 2025
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 Haritz Puerto Martin Gubri Sangdoo Yun Seong Joon Oh MIALM 1.8K 19 3 31 Oct 2024
ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods Roy Xie Junlin Wang Ruomin Huang Minxing Zhang Rong Ge Jian Pei Neil Zhenqiang Gong Bhuwan Dhingra MIALM 556 38 0 23 Jun 2024
Enhancing Contextual Understanding in Large Language Models through Contrastive DecodingNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 Zheng Zhao Emilio Monti Jens Lehmann H. Assem 211 48 0 04 May 2024
Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models Jingyang Zhang Jingwei Sun Eric C. Yeats Ouyang Yang Martin Kuo Jianyi Zhang Hao Frank Yang Hai "Helen" Li 654 78 0 03 Apr 2024
DE-COP: Detecting Copyrighted Content in Language Models Training Data André V. Duarte Xuandong Zhao Arlindo L. Oliveira Lei Li 369 65 0 15 Feb 2024
Low-Cost High-Power Membership Inference AttacksInternational Conference on Machine Learning (ICML), 2023 Sajjad Zarifzadeh Philippe Liu Reza Shokri 320 74 0 06 Dec 2023
Mamba: Linear-Time Sequence Modeling with Selective State Spaces Albert Gu Tri Dao Mamba 546 5,104 0 01 Dec 2023
NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each BenchmarkConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Oscar Sainz Jon Ander Campos Iker García-Ferrero Julen Etxaniz Oier López de Lacalle Eneko Agirre 229 256 0 27 Oct 2023
Proving Test Set Contamination in Black Box Language ModelsInternational Conference on Learning Representations (ICLR), 2023 Yonatan Oren Nicole Meister Niladri Chatterji Faisal Ladhak Tatsunori B. Hashimoto HILM 343 194 0 26 Oct 2023
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot GenerationInternational Conference on Learning Representations (ICLR), 2023 Xinyu Tang Richard Shin Huseyin A. Inan Andre Manoel Fatemehsadat Mireshghallah Zinan Lin Sivakanth Gopi Janardhan Kulkarni Robert Sim 382 89 0 21 Sep 2023
Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities Maximilian Mozes Xuanli He Bennett Kleinberg Lewis D. Griffin 221 106 0 24 Aug 2023
Scalable Membership Inference Attacks via Quantile RegressionNeural Information Processing Systems (NeurIPS), 2023 Martín Bertrán Shuai Tang Michael Kearns Jamie Morgenstern Aaron Roth Zhiwei Steven Wu MIACV 253 68 0 07 Jul 2023
Membership Inference Attacks against Language Models via Neighbourhood ComparisonAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Justus Mattern Fatemehsadat Mireshghallah Zhijing Jin Bernhard Schölkopf Mrinmaya Sachan Taylor Berg-Kirkpatrick MIALM 463 267 0 29 May 2023
Trusting Your Evidence: Hallucinate Less with Context-aware DecodingNorth American Chapter of the Association for Computational Linguistics (NAACL), 2023 Weijia Shi Xiaochuang Han M. Lewis Yulia Tsvetkov Luke Zettlemoyer Scott Yih HILM 230 289 0 24 May 2023
Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Kent K. Chang Mackenzie Cramer Sandeep Soni David Bamman RALM 566 160 0 28 Apr 2023
Pythia: A Suite for Analyzing Large Language Models Across Training and ScalingInternational Conference on Machine Learning (ICML), 2023 Stella Biderman Hailey Schoelkopf Quentin G. Anthony Herbie Bradley Kyle O'Brien ... USVSN Sai Prashanth Edward Raff Aviya Skowron Lintang Sutawika Oskar van der Wal 372 1,616 0 03 Apr 2023
LLaMA: Open and Efficient Foundation Language Models Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux ... Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave Guillaume Lample ALM PILM 4.4K 17,584 0 27 Feb 2023
Extracting Training Data from Diffusion ModelsUSENIX Security Symposium (USENIX Security), 2023 Nicholas Carlini Jamie Hayes Milad Nasr Matthew Jagielski Vikash Sehwag Florian Tramèr Borja Balle Daphne Ippolito Eric Wallace DiffM 457 795 0 30 Jan 2023
GPT-NeoX-20B: An Open-Source Autoregressive Language Model Sid Black Stella Biderman Eric Hallahan Quentin G. Anthony Leo Gao ... Shivanshu Purohit Laria Reynolds J. Tow Benqi Wang Samuel Weinbach 346 947 0 14 Apr 2022
Quantifying Privacy Risks of Masked Language Models Using Membership Inference AttacksConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Fatemehsadat Mireshghallah Kartik Goyal Archit Uniyal Taylor Berg-Kirkpatrick Reza Shokri MIALM 448 204 0 08 Mar 2022
Membership Inference Attacks From First Principles Nicholas Carlini Steve Chien Milad Nasr Shuang Song Seth Neel Florian Tramèr MIACV MIALM 660 905 0 07 Dec 2021
On the Importance of Difficulty Calibration in Membership Inference AttacksInternational Conference on Learning Representations (ICLR), 2021 Lauren Watson Chuan Guo Graham Cormode Alex Sablayrolles 281 171 0 15 Nov 2021
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-ExpertsAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Alisa Liu Maarten Sap Ximing Lu Swabha Swayamdipta Chandra Bhagavatula Noah A. Smith Yejin Choi MU 517 439 0 07 May 2021
The Pile: An 800GB Dataset of Diverse Text for Language Modeling Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe ... Horace He Anish Thite Noa Nabeshima Shawn Presser Connor Leahy AIMat 874 2,526 0 31 Dec 2020
Membership Inference Attacks against Machine Learning Models Reza Shokri M. Stronati Congzheng Song Vitaly Shmatikov SLR MIALM MIACV 866 4,775 0 18 Oct 2016

All Papers

Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding

Papers citing "Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding"