CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades
We introduce CascadeLedger, a counterfactual execution-audit framework for budgeted language-model cascades. The protoco
#cs.LG
共收录 1064 条相关情报。
← 返回所有主题Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
Although Artificial Intelligence (AI)-based Intrusion Detection Systems (IDSs) are increasingly deployed in operational
A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference
Rising privacy concerns around large language models have accelerated research in private Transformer inference (PTI). S
What You Sign Is Not What You Run: The Verifiability Gap in Quantized LLM Supply Chains
Model signing authenticates the full-precision weights W an LLM is released with, yet users run a quantized artifact Q w
Did the LLM Answer the Question? A Semantic Reconstruction Game for Jailbreak Evaluation
Jailbreak attacks against large language models (LLMs) are evaluated using attack success rate (ASR), which depends on c
Autonomous Cyber Operations Gym for Training and Evaluating AI Models for Defence
This paper proposes an Autonomous Cyber Operations (ACO) gym, a unified framework integrating high-fidelity network emul
Limits of Statistical Assurance for Embodied and Agentic AI under Adaptive Adversaries
Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activat
Physical Layer Anomaly Detection via Adaptive Gaussian Mixture Model
Physical-layer spoofing attacks pose a critical threat to wireless localization systems by manipulating channel state in
Towards Safe Autonomy for Computer Use
The safety of LLM-based agents currently rests on alignment training and safety classifiers, neither of which can rule o
Kairos: Transactional Security Enforcement at the System Boundary for LLM Agents
Large language model (LLM) agents are becoming an integral part of the software development lifecycle, and the capabilit
An Initial Study of Physiological Markers for Deepfake Speech Detection
Conventional deepfake speech detectors primarily target synthesis artifacts and often degrade under unseen attacks or re
Privacy-Preserving GNN Inference on Financial Transaction Graphs via Homomorphic Encryption
Anti-money laundering (AML) in financial networks requires modeling transaction patterns that span multiple institutions
BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views
Browser agents need to make decisions and execute actions on behalf of users while consuming untrusted webpages, creatin
Mitigating Black-Box Score-Based Query Attacks via Gradient Confusion
Score-based black-box adversarial attacks pose a serious threat to deployed machine learning systems by exploiting repea
COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration
Vision large language models (VLLMs) are deployed in privacy-sensitive domains, raising training-data exposure concerns.
SSM-Attack: Learning Where to Perturb for Black-Box Face Privacy
Face recognition systems are deployed widely enough that a photograph shared online can be matched without its subject's
Tight End-to-End Accounting for Differentially Private Synthetic Data
Differentially private (DP) pipelines often combine heterogeneous mechanisms, yet their guarantees are best analyzed usi
Can Rényi Accountants Beat Lossless Accountants for DP-SGD?
Recent frameworks in differential privacy (DP), such as privacy loss distributions and $f$-DP, provide lossless represen
Unsupervised Data Drift Monitoring for Deployed Deepfake Speech Detectors
Deepfake speech detectors are typically evaluated as binary classifiers on fixed benchmarks, but deployed systems face e
Differential Privacy Protected Preference Alignment on Survey Derived Data
Preference alignment enables language models to better reflect human values, but the preference data contains sensitive