Towards a Unified Misuse Monitoring Benchmark
LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition at
#cs.LG
共收录 1064 条相关情报。
← 返回所有主题Adaptive-Shot Hybrid Quantum Anomaly Detection for Tactile Internet Security: Reliability-Aware Measurement Allocation Under Resource Constraints
Tactile Internet (TI) security analytics must balance reliable thresholded decisions with constrained computational and
Online AutoML: Evaluating Poisoning Attacks on Adversarial Training Defense Strategy in IoT Networks
Machine learning (ML)-powered poisoning attack vectors are adversarial maneuvers whereby an attacker intentionally inser
Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement
Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing
Visual Grounding Safety in Vision-Language Models
Vision-language models (VLMs) are increasingly trained to generate structured outputs like points and bounding boxes tha
Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential
Mechanistic interpretability has emerged as the primary means to understand safety behavior of LLMs. However, existing t
The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models
该论文关注统一式多模态模型（unified multimodal models）带来的新型隐私威胁。此类模型在同一个对话上下文中既能理解也能生成文本、图像等多种模态，交互更流畅自然，但这一设计也改变了原有的隐私威胁模型：对话某一部分暴露的信
Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks
Self-play red-teaming improves language-model safety by pitting attacker and defender roles against each other in a zero
Private Component-by-Component Learning
We study differentially private learning problems in the realizable setting, where a hypothesis is specified by $k$ comp
Static Bootstrap Placement for Encrypted Language Model Decoding
Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption le
Bounded Reasoning: Cognitive Hierarchy in Human-versus-AI Cyber Defense
Human-agent evaluations often compress interaction into a single performance score, even when human and automated polici
Quantum Machine Learning Protection of Military Quantum Key Distribution Against Cryptographically Camouflaged Attacks
Quantum key distribution proves its protocol secure and says nothing about the hardware beneath it, so military and gove
JASPER: Special Session on Joint Reliability And Security Assessment of SPlit Computing for Edge Robustness
分割计算（Split Computing, SC）通过在边缘设备与云服务器之间切分深度神经网络（DNN）推理来降低端侧算力与延迟压力，但切分点处传输的中间特征表示同时暴露于两类风险：其一是硬件故障（如瞬态位翻转、软错误）导致的推理精度退化，
Modeling Deletion Requests in Machine Unlearning
Machine unlearning is seen as a promising approach to enable users to exercise the "right to erasure" in the context of
CyTReX: Explainable AI-Based Cybersecurity Threat Reasoning Framework for DER Networks
Distributed Energy Resource (DER) environments rely on network communication protocols to coordinate control commands, m
Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience
Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on extern
What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document
Split learning lets a client train a language model on a server without sending its text. The client runs the first laye
Localize-and-Detect: Auditing Task-Level Poisoning in Instruction-Tuned Models
Instruction fine-tuning adapts a pretrained language model to follow instructions by training it on instruction--respons
PoCoFL: POlicy-COmpliant Federated Learning
Federated Learning (FL) is a privacy-oriented learning paradigm that enables collaborative model training while keeping
Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and