Copertina

Towards Independence Criterion in Machine Unlearning of Features and Labels

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Han, Ling, Luo, Nanqing, Huang, Hao, Chen, Jing, Hartley, Mary-Anne
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Cryptography and Security I.2.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Unlearning at Scale: Implementing the Right to be Forgotten in Large Language Models
di: X, Abdullah
Pubblicazione: (2025)

Towards Low-Latency and Adaptive Ransomware Detection Using Contrastive Learning
di: Pan, Zhixin, et al.
Pubblicazione: (2025)

Scalable APT Malware Classification via Parallel Feature Extraction and GPU-Accelerated Learning
di: Subedar, Noah, et al.
Pubblicazione: (2025)

Inverting Cryptographic Hash Functions via Cube-and-Conquer
di: Zaikin, Oleg
Pubblicazione: (2022)

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
di: Zhou, Xueyang, et al.
Pubblicazione: (2025)

A Novel Self-Attention-Enabled Weighted Ensemble-Based Convolutional Neural Network Framework for Distributed Denial of Service Attack Classification
di: S, Kanthimathi, et al.
Pubblicazione: (2024)

SCAFDS: Edge-Feature Graph Attention for Interbank Fraud Detection with Attribution-Grounded SAR Generation
di: Uddin, Mohammad Nasir
Pubblicazione: (2026)

Illuminating the Black Box: Real-Time Monitoring of Backdoor Unlearning in CNNs via Explainable AI
di: Hoang, Tien Dat
Pubblicazione: (2025)

Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions
di: Ma, Jianan, et al.
Pubblicazione: (2026)

Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
di: Cotti, Luca, et al.
Pubblicazione: (2025)

Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents
di: Ravindran, Santhosh Kumar
Pubblicazione: (2026)

MathLedger: A Verifiable Learning Substrate with Ledger-Attested Feedback
di: Abdullah, Ismail Ahmad
Pubblicazione: (2025)

Digital Forgetting in Large Language Models: A Survey of Unlearning Methods
di: Blanco-Justicia, Alberto, et al.
Pubblicazione: (2024)

SAND: A Self-supervised and Adaptive NAS-Driven Framework for Hardware Trojan Detection
di: Pan, Zhixin, et al.
Pubblicazione: (2025)

Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
di: Ahamed, Sayyed Farid, et al.
Pubblicazione: (2025)

Cross-LLM Generalization of Behavioral Backdoor Detection in AI Agent Supply Chains
di: Sanna, Arun Chowdary
Pubblicazione: (2025)

Closing the Distribution Gap in Adversarial Training for LLMs
di: Hu, Chengzhi, et al.
Pubblicazione: (2026)

BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection
di: Cheng, He, et al.
Pubblicazione: (2024)

Multi-Agent Honeypot-Based Request-Response Context Dataset for Improved SQL Injection Detection Performance
di: Yu, Hao, et al.
Pubblicazione: (2026)

SALLIE: Safeguarding Against Latent Language & Image Exploits
di: Azov, Guy, et al.
Pubblicazione: (2026)

Training AI to be Loyal
di: Oh, Sewoong, et al.
Pubblicazione: (2025)

Tatemae: Detecting Alignment Faking via Tool Selection in LLMs
di: Leonesi, Matteo, et al.
Pubblicazione: (2026)

Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget Sensitivity
di: Rashidi, Mohammadreza
Pubblicazione: (2026)

MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
di: Gowda, Ishrith
Pubblicazione: (2026)

Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks
di: Xu, Xinjie, et al.
Pubblicazione: (2025)

A Protocol-Language Model for Network Intrusion (Without Deep Packet Inspection)
di: Sharma, Vivek Kumar
Pubblicazione: (2026)

Binary-30K: A Heterogeneous Dataset for Deep Learning in Binary Analysis and Malware Detection
di: Bommarito II, Michael J.
Pubblicazione: (2025)

Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents
di: Sidik, Bronislav, et al.
Pubblicazione: (2026)

FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning
di: Zhang, Su, et al.
Pubblicazione: (2026)

MM-Food-100K: A 100,000-Sample Multimodal Food Intelligence Dataset with Verifiable Provenance
di: Dong, Yi, et al.
Pubblicazione: (2025)

Activation Differences Reveal Backdoors: A Comparison of SAE Architectures
di: Kumar, Sachin
Pubblicazione: (2026)

A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems
di: Ismail, Nasim Abdirahman, et al.
Pubblicazione: (2026)

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks
di: Feng, Zhou, et al.
Pubblicazione: (2025)

Attacking interpretable NLP systems
di: Abdukhamidov, Eldor, et al.
Pubblicazione: (2025)

Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
di: Lelle, Travis
Pubblicazione: (2026)

David vs. Goliath: Verifiable Agent-to-Agent Jailbreaking via Reinforcement Learning
di: Nellessen, Samuel, et al.
Pubblicazione: (2026)

BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
di: DeLeeuw, Caleb
Pubblicazione: (2026)

SecureV2X: An Efficient and Privacy-Preserving System for Vehicle-to-Everything (V2X) Applications
di: Lee, Joshua, et al.
Pubblicazione: (2025)

Contrastive Self-Supervised Network Intrusion Detection using Augmented Negative Pairs
di: Wilkie, Jack, et al.
Pubblicazione: (2025)

Few-Shot Network Intrusion Detection Using Online Triplet Mining
di: Wilkie, Jack, et al.
Pubblicazione: (2026)