SoK: PIAtlas: Decomposing the Unbounded Prompt Injection Attack Space
Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field sti
#cs.LG
共收录 1064 条相关情报。
← 返回所有主题The Missing Compliance Class: LLM Graders That Collapse Jailbreak Success, and a Free Check
Jailbreak papers report an attack success rate, the share of responses that deliver the harmful request, and read it as
Private Evaluation of High-Dimensional Functions
We study differentially private black-box evaluation of arbitrary high-dimensional functions. Given a dataset $S$ and qu
Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin
To support sustained interactions and personalized assistance, agents use long-term memory to retain and combine user in
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
Predicting CVSS and CWE from CVE Descriptions with Fine-Tuned Small Language Models
Until April 2026, the National Vulnerability Database labeled nearly every published Common Vulnerabilities and Exposure
Recording-Aware Evaluation of Multimodal OT Intrusion Detection
Machine-learning-based intrusion detection systems (IDSs) for operational technology (OT) are commonly evaluated on benc
Task-aware Kernel Stein certificates for Rényi differential privacy
Rènyi differential privacy, based on Rènyi divergence, has become a notion of choice for privacy guarantees. However, ou
ToolRosetta: Surface-Form Invariance of Tool-Call Guards
Step-level guards for tool-using agents are evaluated on tidy JSON tool calls, but deployed coding agents act through ex
HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation
Implementing Security Technical Implementation Guide (STIG) controls remains a demanding operating-system administration
Towards Hyperparameter Transfer for Differentially Private Optimization
Scaling laws and hyperparameter tuning remain central challenges in training large-scale models, particularly under diff
The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems
Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconst
Language Is a Security Surface for Agent Guards
Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the
Shortcut Sensitivity in Agent-Safety Evaluations
AI agents take actions through tools. Some actions are sensitive, so guards that supervise them must themselves be evalu
Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems
Language embeddings are increasingly used in recommenders to represent item content, but their privacy risks remain poor
Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning
Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on us
Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse
Traditional backdoor attacks inject artificial trigger patterns into training data, causing models to misclassify trigge
SHIP: Structured and Hierarchical Insight with Privacy
Extracting insights from textual data while protecting user privacy is increasingly important. Existing methods produce
Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy
We propose a general framework for non-interactive locally differentially private (LDP) learning of structured univariat
Privacy-Preserving Text Inference for Health-Misinformation Classification and Semantic Retrieval
Health-misinformation analysis presents a dual challenge: misleading claims can affect public well-being, while systems