BR-MoE: Budgeted Semantic Release for Privacy-Preserving Traffic Analytics
Traffic cameras support useful analysis, but their outputs can reveal private information. Replacing images with text re
#cs.AI
共收录 1652 条相关情报。
← 返回所有主题Reliable Estimation of Differential Privacy under Selection Bias
Statistical privacy audits are essential for verifying the theoretical privacy guarantees of differentially private (DP)
Fake News, Real Crashes: Information Injection Attacks on LLM Financial Trading Agents
Large language model (LLM) agents now trade real capital using news as evidence, yet they cannot reliably tell fabricate
NIOCIS: Typed-Decision Next-Hop Routing with Node-Conditioned Option Spaces for Tool-Use Agents
Tool-use agents pay per decision: at each hop a language model re-reads the state and thinks for seconds, though its act
Auditor-Assisted Summary-Channel Verification for Hosted LLM Identity Substitution
Hosted LLM services increasingly expose model identity as a product claim, but external users and auditors often cannot
Secure Agentic Coding through Counterexample-Grounded Feedback
As coding models and agent harnesses become more capable, reliable security verification is becoming a central bottlenec
AdaFedXplain: Adaptive Federated Learning with Explainable AI for Ransomware Detection
Attacks using ransomware have developed into complex multiphase campaigns that target vital infrastructure, resulting in
Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On
A guardrail classifier is reported as if unsafe were a property of text. It is not: it is a property of a policy, and th
Same Data, Different Bytes: Serialization-Invariant Integrity Checks for Agent-Published Datasets
Agent networks require reliable ways for requesting agents to verify where data is located, how it can be accessed, and
The One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents
Can one sentence manipulate an agent's belief by targeting a single implicit warrant linking evidence to a conclusion? I
LLM Trojans that Increase Response Lengths and Cost
Management of the token-based costs of using LLMs has emerged as a significant problem. Some frontier-model providers ch
When Code Becomes an LLM Call: An Empirical Study of Call-Site Contracts in Agentic Systems
Software quality has long rested on specifications that state what code must do, and on testing and verification that ch
RATION: Towards Quantitative Risk-Based Access Control for AI Agents
AI agents increasingly interact with external environments to complete complex user tasks. These interactions can lead t
Unbounded Losses, Unchecked Inputs: Measuring the Safeguards of LLM Options-Trading Agents
Large language model (LLM) agents now place options orders at retail brokers, and developers publish open-source options
SPIDES: Information-Flow Control for Browser Agents
Browser agents automate complex workflows by reading and acting on arbitrary page content, but this flexibility exposes
Towards an Intelligent Decision Engine for Smart Contract Deployment
Layer 2 (L2) blockchain solutions emerged in recent years, predominantly in the Ethereum ecosystem, as a viable option f
Red-Teaming Multi-Agent Attacks for Loss-of-Control Risks
AI agents are growing more capable and persistent, and are being deployed in ever larger numbers. As more start collabor
The Window Is in the Reasoning: When LLM Agents Decide to Follow Prompt Injections
LLM agents that read untrusted content can be hijacked by prompt injections. Runtime monitors that try to catch a hijack
TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models
Typed decision models often return more than a selected category. They also expose probabilities for each candidate and,
From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation
Small Language Models (SLMs) are increasingly attractive for resource-constrained environments due to their low computat