Literature Database

SportD: Can VLMs Physically Strategize?

Authors: Jasin Cekinmez, Addison J. Wu, Haotian Xia, Akshaya Bharadhwaj, Anay Putty, Anirudh Ravishankar, Jaewoong Lee, Jinglin Xiao, Kyumin Andrew Shim, Mishika Ahuja, Nisarga Patil, Leo Liu, Zhuohan Liu, Weining Shen | Published: 2026-07-16
Model evaluation methods
行動分析手法
評価基準
2026.07.16 2026.07.18
Literature Database

Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems

Authors: Soham Gadgil, David Alexander, Sai Sunku, Franziska Roesner | Published: 2026-07-16
Indirect Prompt Injection
エージェント操作手法
Threat Model
2026.07.16 2026.07.18
Literature Database

Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms

Authors: Umid Suleymanov, Ilhama Novruzova, Khalid Mammadov, Natavan Hasanova, Murat Kantarcioglu | Published: 2026-07-16
Ensuring Fairness
Bias in Training Data
Differential Privacy
2026.07.16 2026.07.18
Literature Database

Democratizing Agent Deployment Safety: A Structural Monitoring Approach

Authors: Preeti Ravindra, Rahul Tiwari, Vincent Wolowski | Published: 2026-07-16
Challenges in IT Security
Threat Model
評価基準
2026.07.16 2026.07.18
Literature Database

Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation

Authors: Rabimba Karanjai, Yang Lu, Hemanth Hegadehalli Madhavarao, Lei Xu, Weidong Shi | Published: 2026-07-16
Indirect Prompt Injection
攻撃手法の説明
Threat Model
2026.07.16 2026.07.18
Literature Database

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

Authors: Sanket Badhe, Priyanka Tiwari | Published: 2026-07-15
エージェント操作手法
Threat Model
評価基準
2026.07.15 2026.07.17
Literature Database

Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection

Authors: Zhenpeng Li | Published: 2026-07-15
データセットの影響
Threat Model
評価基準
2026.07.15 2026.07.17
Literature Database

Towards quantum machine learning for assessing the resilience of post-quantum cryptography

Authors: Jarosław A. Miszczak | Published: 2026-07-15
Data Augmentation in Encrypted Domains
Generative Model
Quantum Computing Method
2026.07.15 2026.07.17
Literature Database

How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement

Authors: Alexandra E. Michael, Franziska Roesner | Published: 2026-07-15
Indirect Prompt Injection
エージェント操作手法
Threat Model
2026.07.15 2026.07.17
Literature Database

Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities

Authors: Eunna Lee, Jungpyo Nam, Sunjun Hwang | Published: 2026-07-15
Relationship of AI Systems
Data Collection Method
Detection of Hallucinations
2026.07.15 2026.07.17
Literature Database
Next page