Literature Database

TrustJev: Separating Policy Authority from Untrusted Evidence in LLM-Based Decisions

Authors: Zhiwei Xu, Xuyang Liu, Xiaolin Peng, Weixian Deng, Jiabao Gao, Zirui Li, Tian Qiu, Boya Zhou, Wei Jiao, Hai Wan, Xibin Zhao | Published: 2026-10-26
Prompt Injection
Robustness Evaluation
Evaluation Method
2026.10.26 2026.10.28
Literature Database

Scope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition

Authors: Weihang Niu, Mengxing Ren, Che Qu | Published: 2026-10-26
Indirect Prompt Injection
Cyber Threat
攻撃条件と監視
2026.10.26 2026.10.28
Literature Database

From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion

Authors: Ye Lu, Shen Wang, Runze Liu, Zhitao Ou, Haonan Huang, Yihan Yan, Fanghui Sun, Zhaoyang Zhang | Published: 2026-10-26
Deep Learning Model
Evaluation Method
音声プライバシー
2026.10.26 2026.10.28
Literature Database

From Representations to Computational Trajectories: Intrinsic Fingerprinting for Large Language Model Provenance Verification

Authors: Haiyong Tang, Hanzhou Wu, Xinpeng Zhang, Athanasios V. Vasilakos | Published: 2026-10-26
Prompt leaking
Deep Learning Model
Evaluation Method
2026.10.26 2026.10.28
Literature Database

Simulated Control Evals

Authors: Jeffrey Olmo, David Zhang, Tyler Tracy | Published: 2026-10-22
攻撃条件と監視
Evaluation Method
認証手法
2026.10.22 2026.10.24
Literature Database

Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure

Authors: Pellegrino Casoria, Simon Pietro Romano | Published: 2026-10-22
Cyber Threat
Prompt Injection
Evaluation Method
2026.10.22 2026.10.24
Literature Database

Diffusion Language Models for Perplexity-Aware Black-Box Attacks

Authors: Ali Al-Lawati, Elsayed Eshra, Dongwon Lee, Suhang Wang | Published: 2026-10-22
Prompt Injection
Prompt validation
Deep Learning Model
2026.10.22 2026.10.24
Literature Database

AgentPhishing: A Benchmark of LLM Email Agents Under Adaptive Attack

Authors: Justin Tan, Miao Li, Ding Zhao | Published: 2026-10-22
Indirect Prompt Injection
Cyber Threat
Psychological Manipulation
2026.10.22 2026.10.24
Literature Database

Practical Auditing of Differentially Private Graph Release Mechanisms: Methodology, Toolkit, and Case Study

Authors: Nicholas D'Silva, Surya Nepal, Salil S. Kanhere | Published: 2026-10-22
Algorithm
Differential Privacy
Evaluation Method
2026.10.22 2026.10.24
Literature Database

Network topology shapes consensus and vulnerability in LLM populations

Authors: Roberto Passaro, Ariel Flint, Romualdo Pastor-Satorras, Andrea Baronchelli, Luca Maria Aiello | Published: 2026-10-22
Algorithm
Prompt leaking
Deep Learning Model
2026.10.22 2026.10.24
Literature Database
Next page