LEAN: Loss-Engineered Modulation of the Model Weight-Sensitivity Distribution for Efficient, Error-Tolerant Neural Networks
The weights of a trained network do not have uniform sensitivity to model accuracy: the 1% most sensitive weights carry
#cs.LG
共收录 1064 条相关情报。
← 返回所有主题Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt inje
CALLIOPE: Private Insights into AI Use, Without Embeddings
We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g
Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory
Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes i
Privacy Accounting for Empirical Denoisers
Diffusion models have emerged as the foundation of modern generative systems, yet their high memorization capacity raise
CyberHull: Deterministic Malicious URL Isolation via Convex Hull
The emergence of increasingly sophisticated and evasion-resistant phishing attack strategies represents a significant th
Bridging Digital Deception and Physical Fidelity: A Spatio-Temporal Attack on Cognitive Radars
As cognitive radars evolve towards the end-to-end processing of one-dimensional complex baseband sequences, deep network
Beyond the Prompt: Recovering Hidden Concepts in Text-to-Image Models
Text-to-image models can generate visual concepts that their prompts never mention, and recent work shows that such asso
Global Security Blind Spots: Translation as a Safety Bypass in Low-Resource Languages
Large language models are deployed globally, yet safety alignment and evaluation remain concentrated in English: harmful
Guided Diffusion for Trustworthy Synthetic Text Generation
The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks
You Are the Trigger: Speaker-Activated Backdoors
Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing au
Reliable Estimation of Differential Privacy under Selection Bias
Statistical privacy audits are essential for verifying the theoretical privacy guarantees of differentially private (DP)
LeakBench: Auditing Reward Hacking through Prediction-Time Leakage in Clinical Modeling Agents
Autonomous clinical-modeling agents can optimize predictive performance while violating conditions that make a model usa
SPLASH: Contrastive Audit Pressure for Detecting and Localizing Security Hallucinations in Generated Code
Code generated by large language models often passes every functional test while remaining insecure. These security hall
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
Fundamental Limits of Information-Theoretic Secure Aggregation with User Dropouts in Federated Learning
Secure aggregation enables a server to compute the sum of users' gradients or model updates without revealing individual
GreenNIDS: A Benchmark Workflow and Analysis Dataset for NetFlow Intrusion Detection Experiments
Comparing the predictive performance and computational cost of flow-based intrusion detection experiments requires both
Federated Learning for Malware Image Classification under Data Heterogeneity
Malware image classification (MIC), in which binary files are converted into visual representations and deep neural netw
Many Repairs, One Direction: Steering Code Models Toward Safer Cryptographic API Use
Cryptographic API misuse in large language model-generated code can compromise software security. While many existing ap
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