Difficulty Calibration Across Time for Membership Inference in Diffusion Models
Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inf
#cs.LG
共收录 1064 条相关情报。
← 返回所有主题Deep Learning Based Behavioral Drift Modeling for Continuous Biometric Authentication
This research proposes a two-level keystroke dynamics authentication system that provides defense-in-depth security thro
DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning
As network scale and uncertainty complicate automated penetration testing, reinforcement learning (RL) environments must
Surprise Alone Learns Lies: Evidence-Gated Continual Learning for LLMs from Streaming Claims
Continual learning methods for large language models increasingly decide what to learn by surprise, keeping the inputs t
Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection
Automated detection has become the essential safeguard against realistic synthetic media, but deploying it at scale requ
DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3
Customizing Pretrained Models (PMs) for downstream tasks demands task-specific data, which burgeoning Web3 applications
Where You Inject Matters: The Trust Region Effect in LLM Agents
LLM agents are increasingly adopted in long-horizon tasks and interact with diverse external environments. Despite their
Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness
Distributed machine learning (DML), including conventional distributed training and federated learning (FL), enables col
Recurrent Bipartite Graph Neural Networks for QC-MDPC Error Decoding in McEliece Cryptosystems
As the advent of large-scale quantum computing threatens classical encryption, Quasi-Cyclic Moderate Density Parity-Chec
Jailbreak Connectivity: Towards Diverse, Transferable, and Universal Multimodal Large Language Model Jailbreak
Multimodal large language models (MLLMs) are vulnerable to visual jailbreak attacks that bypass safety safeguards. Exist
Progressive-Observation Physical-Layer Fingerprinting for Efficient Open-Set Ethernet Authentication
Physical-layer fingerprinting (PLF) has emerged as a promising authentication approach for Internet of Things devices. H
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small s
Agentic Backdoors via Pretraining Poisoning
Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security ris
Watermark Basins: Black-Box Detection of Distilled LLMs
Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trai
When Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning
Multi-relational graph detectors learn from clean data how much to trust each relation, but an adversary pays a differen
Blindfold: Keeping the Audit Coin Secret from LLM Agents
Audit-based certification bounds the violation rate of an LLM agent by auditing a random fraction $\varepsilon$ of actio
Quantifying and Prioritizing Stealthy Source-Manipulation Threats Against Multi-Source Anomaly Detectors
Security pipelines often fuse several data sources and protect a downstream model with a cross-source anomaly detector.
Generation, Not Selection: LLM Proposals for Certified Access-Control Policy Mining
Attribute-Based Access Control (ABAC) policy mining---recovering a compact, auditable policy from an access log---is pos
Split Federated Unlearning
Split federated learning (SFL) combines partitioned model execution with federated aggregation to support collaborative
A Simple Presentation of Robust Membership Inference Attacks
In a membership inference attack, an attacker is given the data of a particular individual, and tries to determine if th