Power Side-Channel Membership Inference Attack on Embedded Machine Learning
Membership inference attacks (MIAs) threaten the privacy of machine learning (ML) training data by determining whether a
#cs.LG
共收录 1064 条相关情报。
← 返回所有主题CPU-Auth: Device Fingerprinting for Authentication via DVFS Side-Channel
Lack of effective authentication has resulted in numerous security and privacy breaches, including unauthorized access t
Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning
Large Language Models (LLMs) inevitably internalize substantial amounts of sensitive or private information during pre-t
PatchBench: Measuring Collateral Damage in Activation Patching
An LLM safety patch can pass a benchmark while still being a poor repair. This risk is especially acute for jailbreak re
PairAudit: Guiding Human Review with Graph Tokens under Distribution Shift
Intrusion detectors can confidently misclassify attacks that were not seen during training. Human review can correct the
Efficient Provably Private Classification with a Tabular Foundation Model
Tabular data underpin prediction and decision-making in medicine, finance, government and science, but often contain sen
Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models
Looped Language Models (LoopLMs) provide a parameter efficient approach to scaling model capabilities through repeated u
Pareto-optimal quantum kernel selection for unsupervised anomaly detection on real malware beaconing data
Quantum kernel methods are leading candidates for a practical quantum advantage in machine learning, but assessing that
Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs
Token-Pruning accelerates Vision-Language Models by removing redundant visual tokens, yet its safety implications remain
Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD
DP-SGD protects training data by adding Gaussian noise to clipped gradients. The amount of noise is usually chosen by ru
MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness certif
When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry
Mixture-of-Experts (MoE) language models produce routing information during inference that may be logged or exposed for
Temporal transformer CAN encoder with federated lightweight heads for anomaly detection
Modern vehicles rely on large numbers of Electronic Control Units (ECUs) that constantly exchange information over the C
Constitution-Guided Watermarking
Watermarking enables language model providers to identify text generated by their models. However, its desired propertie
Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense
Policy-based reinforcement learning (RL) approaches have produced promising results for autonomous cyber defense; howeve
Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs
Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while mode
Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models
Does removing harmful information make open-weight models resistant to fine-tuning attacks? We show that mutual informat
How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis
As small language models (SLMs) are increasingly deployed on resource-constrained and on-device platforms, including as
Secure Speculative Decoding for Large Language Models
Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by
RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems
Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in retrieved content. W