Imagen de Portada

Reconstruction of Personally Identifiable Information from Supervised Finetuned Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Furukawa, Sae, Oprea, Alina
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

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

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

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

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

Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs
por: Joshi, Kunj, et al.
Publicado: (2025)

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

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

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

Personal Information Parroting in Language Models
por: Subramani, Nishant, et al.
Publicado: (2026)

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

Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
por: Halawi, Danny, et al.
Publicado: (2024)

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

MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
por: Jiang, Weisen, et al.
Publicado: (2025)

When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
por: Xu, Xiaoyu, et al.
Publicado: (2026)

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

Synthesizing Tight Privacy and Accuracy Bounds via Weighted Model Counting
por: Oakley, Lisa, et al.
Publicado: (2024)

Syntax- and Compilation-Preserving Evasion of LLM Vulnerability Detectors
por: Sun, Luze, et al.
Publicado: (2026)

Automated CVE Analysis: Harnessing Machine Learning In Designing Question-Answering Models For Cybersecurity Information Extraction
por: Faruk, Tanjim Bin
Publicado: (2024)

Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training
por: Zhao, Shuai, et al.
Publicado: (2024)

Detecting Pretraining Data from Large Language Models
por: Shi, Weijia, et al.
Publicado: (2023)

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

Securing Large Language Models (LLMs) from Prompt Injection Attacks
por: Suri, Omar Farooq Khan, et al.
Publicado: (2025)

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

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
por: Yin, Haoteng, et al.
Publicado: (2024)

On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models
por: Sahili, Ali Al, et al.
Publicado: (2025)

Watermarking Language Models through Language Models
por: Dasgupta, Agnibh, et al.
Publicado: (2024)

Model Provenance Testing for Large Language Models
por: Nikolic, Ivica, et al.
Publicado: (2025)

Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
por: Kaneko, Masahiro, et al.
Publicado: (2025)

Malware Classification from Memory Dumps Using Machine Learning, Transformers, and Large Language Models
por: Dweib, Areej, et al.
Publicado: (2025)

What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference
por: Fan, Mingyuan, et al.
Publicado: (2026)

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

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

Quantitative Resilience Modeling for Autonomous Cyber Defense
por: Cadet, Xavier, et al.
Publicado: (2025)

Towards the Anonymization of the Language Modeling
por: Boutet, Antoine, et al.
Publicado: (2025)

On the Learnability of Watermarks for Language Models
por: Gu, Chenchen, et al.
Publicado: (2023)

A Watermark for Large Language Models
por: Kirchenbauer, John, et al.
Publicado: (2023)

Localizing Paragraph Memorization in Language Models
por: Stoehr, Niklas, et al.
Publicado: (2024)

Are PPO-ed Language Models Hackable?
por: Anand, Suraj, et al.
Publicado: (2024)

On the Reliability of Watermarks for Large Language Models
por: Kirchenbauer, John, et al.
Publicado: (2023)