Cover Image

Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Xingli, Kim, Jung-Eun
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Representation Magnitude has a Liability to Privacy Vulnerability
by: Fang, Xingli, et al.
Published: (2024)

Decoupling Generalizability and Membership Privacy Risks in Neural Networks
by: Fang, Xingli, et al.
Published: (2026)

Center-Based Relaxed Learning Against Membership Inference Attacks
by: Fang, Xingli, et al.
Published: (2024)

Trustworthy AI: Safety, Bias, and Privacy -- A Survey
by: Fang, Xingli, et al.
Published: (2025)

Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation
by: Li, Jianwei, et al.
Published: (2026)

Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
by: Li, Jianwei, et al.
Published: (2026)

Your Privacy Depends on Others: Collusion Vulnerabilities in Individual Differential Privacy
by: Kaiser, Johannes, et al.
Published: (2026)

Learnable Privacy Neurons Localization in Language Models
by: Chen, Ruizhe, et al.
Published: (2024)

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
by: Li, Jianwei, et al.
Published: (2025)

CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs
by: Arachchige, Shashie Dilhara Batan, et al.
Published: (2025)

Inducing Uncertainty on Open-Weight Models for Test-Time Privacy in Image Recognition
by: Ashiq, Muhammad H., et al.
Published: (2025)

RL-Finetuned LLMs for Privacy-Preserving Synthetic Rewriting
by: Shi, Zhan, et al.
Published: (2025)

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
by: Struppek, Lukas, et al.
Published: (2026)

Statement-Level Vulnerability Detection: Learning Vulnerability Patterns Through Information Theory and Contrastive Learning
by: Nguyen, Van, et al.
Published: (2022)

Rethinking the Vulnerability of Concept Erasure and a New Method
by: Richardson, Alex D., et al.
Published: (2025)

Causal Discovery Under Local Privacy
by: Binkytė, Rūta, et al.
Published: (2023)

Robust Privacy: Inference-Time Privacy through Certified Robustness
by: Jin, Jiankai, et al.
Published: (2026)

Superficial Safety Alignment Hypothesis
by: Li, Jianwei, et al.
Published: (2024)

Beyond Data Privacy: New Privacy Risks for Large Language Models
by: Du, Yuntao, et al.
Published: (2025)

Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
by: Peng, Benji, et al.
Published: (2024)

Finetuning Large Language Models for Vulnerability Detection
by: Shestov, Alexey, et al.
Published: (2024)

RAG with Differential Privacy
by: Grislain, Nicolas
Published: (2024)

ACU: Analytic Continual Unlearning for Efficient and Exact Forgetting with Privacy Preservation
by: Tang, Jianheng, et al.
Published: (2025)

PassREfinder-FL: Privacy-Preserving Credential Stuffing Risk Prediction via Graph-Based Federated Learning for Representing Password Reuse between Websites
by: Kim, Jaehan, et al.
Published: (2025)

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

Enhancing Vulnerability Reports with Automated and Augmented Description Summarization
by: Althebeiti, Hattan, et al.
Published: (2025)

Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems
by: Rathnasuriya, Ravishka, et al.
Published: (2025)

ARVO: Atlas of Reproducible Vulnerabilities for Open Source Software
by: Mei, Xiang, et al.
Published: (2024)

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
by: Li, Yuxi, et al.
Published: (2024)

ST-DPGAN: A Privacy-preserving Framework for Spatiotemporal Data Generation
by: Shao, Wei, et al.
Published: (2024)

In-Context Unlearning: Language Models as Few Shot Unlearners
by: Pawelczyk, Martin, et al.
Published: (2023)

The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets
by: Ganev, Georgi, et al.
Published: (2023)

Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning
by: Foroughi, Mohammad Hadi, et al.
Published: (2026)

Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices
by: Abdali, Sara, et al.
Published: (2024)

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques
by: Jaffal, Niveen O., et al.
Published: (2025)

Can Neural Decompilation Assist Vulnerability Prediction on Binary Code?
by: Cotroneo, D., et al.
Published: (2024)

Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack
by: Yue, Murong, et al.
Published: (2025)

Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models
by: Krishna, Arjun, et al.
Published: (2025)

An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graph
by: Islam, Nafis Tanveer, et al.
Published: (2023)

How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers
by: Zhang, Guangsheng, et al.
Published: (2022)