HE-OFT: Privacy-Preserving One-Shot Federated Fine-Tuning under Homomorphic Encryption
Many organizations adapt large pretrained models to their own tasks by fine-tuning on private data. Several of these par
#cs.LG
共收录 1064 条相关情报。
← 返回所有主题On the Intrinsic Limited Robustness of Latent-Based Watermarking
Existing latent-based watermarking methods for diffusion models have overestimated their robustness to image distortions
Surviving the Router: Optimizing Skill Injections for Retrieval and Execution
AI agents increasingly rely on modular third-party "skills" that are dynamically selected by skill routers to execute co
Explainable Rule Mining of IPv6 Extension-Header Presence Patterns from Paired-Vantage Captures
IPv6 extension headers (EHs), such as fragmentation, segment routing, and in-situ telemetry, are operationally important
The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almo
Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff
In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underes
Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates
Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and
Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security
Increasing connectivity to the outside world and the lack of inbuilt security mechanisms have made legacy intra-vehicula
Evaluating Behavioral Context for Interpretable IAM Policy Risk Scoring in Cloud Environments
IAM policy analysis typically emphasizes the authorization capabilities encoded in a policy, but security analyst review
Weight Oracles: Reading Neural Network Weights with Language Models
Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specif
ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning
Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of a
Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents
Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately
Reward-Driven Learning under Prompt-Level Differential Privacy
Reinforcement learning with verifiable rewards (RLVR) trains a language model on problems that may themselves be confide
Private online learning and prediction for Littlestone classes
We study mistake bounds for differentially private online learning and online prediction under oblivious realisable adve
Jailbreaking Open-Weight LLMs via Random Embedding Perturbations
While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their s
Differentially Private Mixing of Public Datasets Improves Private Learning
Many machine learning applications involve sensitive data and therefore require training under differential privacy (DP)
Efficient Secure Federated Learning via Information-Theoretically Secure Key Distribution: A Medical Imaging Case Study
Federated Learning (FL) enables collaborative training of models across institutions without centralizing sensitive data
RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external
Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning
Large Language Models (LLMs) are increasingly deployed for automated software vulnerability analysis. Binary classificat
Watermarking: from Impossibility to Auditable Compliance
Article 50 (2) of the EU Artificial Intelligence Act requires providers of generative systems to make synthetic outputs