Image de couverture de livre

Position: No Retroactive Cure for Infringement during Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Utsunomiya, Satoru, Isonuma, Masaru, Mori, Junichiro, Sakata, Ichiro
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ME: Trigger Element Combination Backdoor Attack on Copyright Infringement
par: Yang, Feiyu, et autres
Publié: (2025)

Towards Transfer Unlearning: Empirical Evidence of Cross-Domain Bias Mitigation
par: Lu, Huimin, et autres
Publié: (2024)

UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
par: Lu, Huimin, et autres
Publié: (2025)

Multi-Agent Optimization for Safety Analysis of Cyber-Physical Systems: Position Paper
par: Gürcan, Önder, et autres
Publié: (2024)

Combating Data Laundering in LLM Training
par: Li, Muxing, et autres
Publié: (2026)

Persistent Pre-Training Poisoning of LLMs
par: Zhang, Yiming, et autres
Publié: (2024)

Neural Network Training on Encrypted Data with TFHE
par: Montero, Luis, et autres
Publié: (2024)

LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks
par: Zhang, Qingzhao, et autres
Publié: (2024)

Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
par: Lin, Chenhao, et autres
Publié: (2025)

GPT-Enabled Cybersecurity Training: A Tailored Approach for Effective Awareness
par: Al-Dhamari, Nabil, et autres
Publié: (2024)

Substituting Proof of Work in Blockchain with Training-Verified Collaborative Model Computation
par: Rafid, Mohammad Ishzaz Asif, et autres
Publié: (2025)

Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Training
par: Khan, Tanveer, et autres
Publié: (2024)

Post-Training Local LLM Agents for Linux Privilege Escalation with Verifiable Rewards
par: Normann, Philipp, et autres
Publié: (2026)

Poster: ClawdGo: Endogenous Security Awareness Training for Autonomous AI Agents
par: Li, Jiaqi, et autres
Publié: (2026)

How to Train your Antivirus: RL-based Hardening through the Problem-Space
par: Tsingenopoulos, Ilias, et autres
Publié: (2024)

Towards Understanding and Enhancing Security of Proof-of-Training for DNN Model Ownership Verification
par: Chang, Yijia, et autres
Publié: (2024)

Ents: An Efficient Three-party Training Framework for Decision Trees by Communication Optimization
par: Lin, Guopeng, et autres
Publié: (2024)

Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Security
par: Wang, Haodi, et autres
Publié: (2024)

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training
par: Du, Pengfei
Publié: (2025)

Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?
par: MacDermott, Matt, et autres
Publié: (2025)

How To Think About End-To-End Encryption and AI: Training, Processing, Disclosure, and Consent
par: Knodel, Mallory, et autres
Publié: (2024)

AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs
par: Lazier, Lara Magdalena, et autres
Publié: (2025)

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models
par: Ding, Zikang, et autres
Publié: (2026)

Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning
par: Yang, Ze, et autres
Publié: (2025)

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
par: Dai, Muzhi, et autres
Publié: (2025)

AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises
par: Tung, Ivan K., et autres
Publié: (2026)

Proactive DDoS Detection and Mitigation in Decentralized Software-Defined Networking via Port-Level Monitoring and Zero-Training Large Language Models
par: Swileh, Mohammed N., et autres
Publié: (2025)

Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation
par: Li, Jianwei, et autres
Publié: (2026)

Position: Explain to Question not to Justify
par: Biecek, Przemyslaw, et autres
Publié: (2024)

The Role and Applications of Airport Digital Twin in Cyberattack Protection during the Generative AI Era
par: Weinberg, Abraham Itzhak
Publié: (2024)

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning
par: Li, Shenghui, et autres
Publié: (2024)

MaXsive: High-Capacity and Robust Training-Free Generative Image Watermarking in Diffusion Models
par: Mao, Po-Yuan, et autres
Publié: (2025)

Position: AI Security Policy Should Target Systems, Not Models
par: Riegler, Michael A., et autres
Publié: (2026)

Position: Challenges and Opportunities for Differential Privacy in the U.S. Federal Government
par: Khanna, Amol, et autres
Publié: (2024)

Adaptive Discounting of Training Time Attacks
par: Bector, Ridhima, et autres
Publié: (2024)

Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systems
par: Bucknall, Ben, et autres
Publié: (2025)

AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs
par: Lv, Lijia, et autres
Publié: (2024)

Leveraging RAG for Training-Free Alignment of LLMs
par: Halloran, John T.
Publié: (2026)

Extracting Memorized Training Data via Decomposition
par: Su, Ellen, et autres
Publié: (2024)

Optimistic Verifiable Training by Controlling Hardware Nondeterminism
par: Srivastava, Megha, et autres
Publié: (2024)