CryptoFlowBench: Benchmarking Multi-Hop Reasoning on Blockchains for Cryptocurrency Fund Tracing
Pseudonymous accounts and complex smart-contract ecosystems substantially hinder the tracing of illicit cryptocurrency f
#cs.LG
共收录 1064 条相关情报。
← 返回所有主题Hardware-Assisted Multi-Stage Ransomware Detection with Adaptive Machine Learning
Ransomware is a fast-escalating privacy threat causing significant financial and data losses worldwide. As attacks grow
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn com
To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse
Cross-model KV cache sharing reduces prefill computation by allowing a receiver model to reuse prefix KV states generate
Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging
Deep learning is now central to radiology, helping detect changes on X-rays, CTs, and MRIs. However, these systems are h
Poisoned into Action: Context Attacks on Typed Decision Workflows
Typed decision interfaces restrict models to predefined actions, yet schema-valid choices can still trigger policy-viola
From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents
Audio Large Language Models (Audio LLMs) are embedded in agents for smart homes, vehicles, wearables, and embodied syste
Accuracy and Uncertainty in Machine Deception Detection (Research White Paper)
A deception detector is only as useful as the trust its alarms deserve. Like a polygraph, detectors that read a language
Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models
Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in whi
AI Models Can Provably Hide Arbitrary Capabilities
Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the
The Limits of Query Monitoring against Distributed Model Extraction
Model providers now face distillation campaigns run through thousands of accounts, each of which looks like an ordinary
Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors
Some backdoor attacks never touch an image. FLIP only changes labels: on CIFAR-10, flipping 3% of them makes a ResNet-32
VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
LLM agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can
Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing
Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The d
PVBRF-ID: Private, Verifiable and Byzantine-Robust Federated Intrusion Detection for Oilfield Enterprise Networks
Federated learning allows dispersed oilfield sites to train a shared intrusion detector without pooling network traffic,
Verification with Transfer: Exact Information Frontiers and Their Price in Calls
A verifier that accepts or rejects whole answers reveals little: under a flat prior over $k$-bit answers, zero error nee
Poster: A Preliminary Study of LLM Distillation Inference
Unauthorized model distillation, in which a model is trained on the outputs of a proprietary large language model (LLM),
Could LLM Watermark Detection be Public?
Watermarking large language models is popular for tracing chatbot and agentic outputs, yet detectors remain unreleased s
BRACE: Differential Privacy for Dense Associative Memory with LSR Energy
Dense associative memory (DAM) provides an energy-based framework for memory retrieval with close connections to attenti
NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents
Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules