001 Prompting Rules That Reduce Codex Mojibake Accidents on Windows (archived 2026-07-27) OpenAlex Paper Go Komura 5 days ago 002 Prompting Rules That Reduce Codex Mojibake Accidents on Windows (archived 2026-07-27) OpenAlex Paper Go Komura 5 days ago 003 Agents reading web pages, emails and repository files are hijacked by prompt injections hidden in untrusted content, yet 2026 benchmarks show deployed guards over-block benign text, making them unusable inline. A naive single prompt asking a base model whether text is an injection fails because without the agent's declared task it cannot separate legitimate imperative content, such as a README's install instructions, from instructions subverting the agent, returning a bare score with no offending span or operating point. Evaluate a task-conditioned LLM judge seeing the declared task and permitted capabilities alongside the untrusted output, using constrained structured decoding to emit is_injection, targeted_capability, quoted span and confidence, retrieving injection patterns for few-shot grounding, and applying a threshold calibrated on a benign corpus with self-consistency voting. Measure ROC-AUC, recall at sub-one-percent false-positive rate, span-localization precision and Brier calibration on AgentDojo-style labeled attack traces plus held-out benign corpora, beating a naive single-prompt base-model classifier and a Llama-Guard-style guardrail. Deliver as the prototype a minimal runnable Python MCP server (stdio) exposing the priced AI tool screen_tool_output that invokes a language or ML model to produce its output, with a typed input/output schema, an x402-style pay-per-call metering stub that records a per-call price in USDT and emits a settlement receipt, and one smoke test that exercises the tool end to end. OpenAlex Paper Dogukan Ali Gundogan Jul 24 004 Agents reading web pages, emails and repository files are hijacked by prompt injections hidden in untrusted content, yet 2026 benchmarks show deployed guards over-block benign text, making them unusable inline. A naive single prompt asking a base model whether text is an injection fails because without the agent's declared task it cannot separate legitimate imperative content, such as a README's install instructions, from instructions subverting the agent, returning a bare score with no offending span or operating point. Evaluate a task-conditioned LLM judge seeing the declared task and permitted capabilities alongside the untrusted output, using constrained structured decoding to emit is_injection, targeted_capability, quoted span and confidence, retrieving injection patterns for few-shot grounding, and applying a threshold calibrated on a benign corpus with self-consistency voting. Measure ROC-AUC, recall at sub-one-percent false-positive rate, span-localization precision and Brier calibration on AgentDojo-style labeled attack traces plus held-out benign corpora, beating a naive single-prompt base-model classifier and a Llama-Guard-style guardrail. Deliver as the prototype a minimal runnable Python MCP server (stdio) exposing the priced AI tool screen_tool_output that invokes a language or ML model to produce its output, with a typed input/output schema, an x402-style pay-per-call metering stub that records a per-call price in USDT and emits a settlement receipt, and one smoke test that exercises the tool end to end. OpenAlex Paper Dogukan Ali Gundogan Jul 24 005 VirtualSet: Typed Ontology Worlds as an LLM Generation Target for Grounded Queries and Guarded Decisions OpenAlex Paper Qunhui Zhang Jul 21 006 VulGen: Workshop on Vulnerabilities in Generative Systems for Information Retrieval OpenAlex Paper Shuoqi Sun, Sara Fahad Dawood Al Lawati et al. Jul 10 007 RAG ile kurumsal yapay zekâ asistanı geliştirmek: Bir öğrenci destek hizmetleri asistanı örneği OpenAlex Paper Fatma Topuz Eryürük, Mehmet Fırat Jul 6 008 Research - Totp Vault Authenticator OpenAlex Paper Lois-Kleinner Alpasan Jun 20 009 Research - Totp Vault Authenticator OpenAlex Paper Lois-Kleinner Alpasan Jun 20 010 SMTQuery: A novel tool for analyzing SMT-LIB string benchmarks OpenAlex Paper Mitja Kulczynski, Kevin Lotz et al. Jun 19 011 Adversarial AI Evaluating Prompt Injection Vectors for Cyber Reconnaissance in Indian Governance Infrastructure OpenAlex Paper Saranyo Deyasi Jun 18 012 Adversarial AI Evaluating Prompt Injection Vectors for Cyber Reconnaissance in Indian Governance Infrastructure OpenAlex Paper Saranyo Deyasi Jun 18 013 AltayDuel: A Turkish-First Arena and Open Dataset for Multi-Turn LLM Prompt-Injection Red-Teaming OpenAlex Paper Fevzi Ege Yurtsevenler Jun 13 014 AltayDuel: A Turkish-First Arena and Open Dataset for Multi-Turn LLM Prompt-Injection Red-Teaming OpenAlex Paper Fevzi Ege Yurtsevenler Jun 13 015 XMR: Exact Match Recovery for Evaluating Text Normalization Against Adversarial Unicode Attacks OpenAlex Paper Richard Quinn Jun 9 016 Rule-Based SQL Grammar Validator OpenAlex Paper Syahrul Fajar Laqsono, Agung Prasetya et al. Jun 6 017 Evaluating Prompt Injection Defenses in Large Language Models: A Multi-Model Empirical Study of Security–Usability Trade-offs OpenAlex Paper Robert Kemp May 31 018 AI-Assisted Vulnerability Discovery and Reporting: Reliability Challenges, Security Risks, and Future Directions OpenAlex Paper Shaik Mohammad Yasin, Kalisetti Venkatesh et al. May 29 019 The Summarization Trap: Quantifying Role-Based Vulnerabilities and Lexical Hijacking in RAG Pipelines OpenAlex Paper Aswin Balaji Aswin Balaji May 24 020 The Summarization Trap: Quantifying Role-Based Vulnerabilities and Lexical Hijacking in RAG Pipelines OpenAlex Paper Aswin Balaji Aswin Balaji May 24 021 SQLsaber: Agentic SQL Assistant for Efficient and High-Accuracy Natural Language Database Exploration OpenAlex Paper Sarthak Jariwala May 22 022 Data extraction dataset for a systematic literature review on prompt-based attacks and defenses in Large Language Models OpenAlex Paper Victória Guimarães, Débora da Costa Medeiros et al. May 21 023 Data extraction dataset for a systematic literature review on prompt-based attacks and defenses in Large Language Models OpenAlex Paper Victória Guimarães, Débora da Costa Medeiros et al. May 21 024 Cyber Range Ethical Pretesting And Reporting Platform OpenAlex Paper Azhar Khan May 20 025 Cyber Range Ethical Pretesting And Reporting Platform OpenAlex Paper Azhar Khan May 20 026 Dialect-Agnostic SQL Parsing via LLM-Based Segmentation OpenAlex Paper Junwen An, Kabilan Mahathevan et al. May 18 027 Intelligent Resume Generation Using Generative AI and Full-Stack Web Technologies OpenAlex Paper Anmoldeep Chauhan, Manju Lata, Rajendra Singh May 14 028 FlexPDF: Unveiling the Potential of Client-Side Web Technologies for Privacy-Preserving Document and Image Processing OpenAlex Paper Pranjal Srivastava May 8 029 GLITCH_AI: A Hybrid Framework for Automated Penetration Testing with LLM-Driven Adaptation and Reporting OpenAlex Paper Maria Gonzalez Herrero, Amit Kumar Singh et al. May 8 030 From Ambiguous Queries to Verifiable Insights: A Task‐Driven Framework for LLM‐Powered SOC Analysis <sup>⋆</sup> OpenAlex Paper H ZHANG, Haiyan Wang et al. May 4 031 SynSQL: Synthesizing Relational Databases for Robust Evaluation of Text-to-SQL Systems OpenAlex Paper Mohammadamin Habibollah, Davood Rafiei Apr 29 032 Leveraging Large Language Models for Advanced Penetration Testing and Vulnerability Analysis OpenAlex Paper Shreyansh Jain, Jyothi Shanbhag et al. Apr 28 033 AI-Enabled Domain Adaptation Technique for Automated IoT Vulnerability Detection and Mitigation OpenAlex Paper K.Benazeer Fathima, J.Nishanthi et al. Apr 21 034 Improving Safety Deep Learning-Based Vulnerability Detection OpenAlex Paper Samir Haddad, Kassem Hamze et al. Apr 21 035 Sentinel Model as a Try: a dual-Model Architecture for Defending against Data Extraction Attacks in Retrieval-Augmented Generation OpenAlex Paper Jianghui Hu, Na Fan et al. Apr 21 036 ScenGDL: Smart contract vulnerability detection and location based on temporal Scenarios and Graph convolution networks OpenAlex Paper Xinyi Shen, Xiangfu Zhao et al. Apr 18 037 The Last Developer: App, Android, VBA, Matlab, and Embedded — How AI Collapsed Every Software Moat, and Why Formal Verification Is the Only Proof That Remains OpenAlex Paper Rajeshkumar Venugopal Apr 18 038 The Last Developer: App, Android, VBA, Matlab, and Embedded — How AI Collapsed Every Software Moat, and Why Formal Verification Is the Only Proof That Remains OpenAlex Paper Rajeshkumar Venugopal Apr 18 039 Evaluating open-source LLMs for dental EMR generation OpenAlex Paper Hao Wang, Wen Du et al. Apr 17 040 Interpretable SQL Injection Detection: Lightweight Decision Trees with SHAP-Enhanced Deployment OpenAlex Paper Showkot Hosen, Abdullah Al Mamun Zihan et al. Apr 16 041 The Last Developer: App, Android, VBA, Matlab, and Embedded — How AI Collapsed Every Software Moat, and Why Formal Verification Is the Only Proof That Remains OpenAlex Paper Rajeshkumar Venugopal Apr 14 042 The Last Developer: App, Android, VBA, Matlab, and Embedded — How AI Collapsed Every Software Moat, and Why Formal Verification Is the Only Proof That Remains OpenAlex Paper Rajeshkumar Venugopal Apr 14 043 GUI Based Natural Language Interface for Database Querying OpenAlex Paper G. Lalithya, M. V. Gnana Prasuna et al. Apr 12 044 GUI Based Natural Language Interface for Database Querying OpenAlex Paper G. Lalithya, M. V. Gnana Prasuna et al. Apr 12 045 The Last Developer: App, Android, VBA, Matlab, and Embedded — How AI Collapsed Every Software Moat, and Why Formal Verification Is the Only Proof That Remains OpenAlex Paper Rajeshkumar Venugopal Apr 12 046 The Last Developer: App, Android, VBA, Matlab, and Embedded — How AI Collapsed Every Software Moat, and Why Formal Verification Is the Only Proof That Remains OpenAlex Paper Rajeshkumar Venugopal Apr 12 047 Replication Package for "Look Back Before You Bisect: A Risk-Aware Approach for Efficient Bisection" OpenAlex Paper Ali Sayedsalehi, Peter C. Rigby Apr 1 048 Replication Package for "Look Back Before You Bisect: A Risk-Aware Approach for Efficient Bisection" OpenAlex Paper Ali Sayedsalehi, Peter C. Rigby Apr 1 049 ЖЕЛІ АРҚЫЛЫ ЖАЛҒАН КОНТЕНТТІ ТАСЫМАЛДАУДЫ ІЗДЕУ ҮШІН ЖЕЛІЛІК ТРАФИКТІ ТАЛДАУ OpenAlex Paper З.А. Сарсембаева, Г.И. Аймичева et al. Mar 30 050 XMR: Exact Match Recovery for Evaluating Text Normalization Against Adversarial Unicode Attacks OpenAlex Paper Richard Quinn Mar 29 051 Chinese semantic obfuscation blackbox jailbreak for domestic large models OpenAlex Paper Xinxin Yue, Zhiyong Zhang et al. Mar 26 052 Detecting and Mitigating AI Prompt Injection Attacks in Large Language Models (LLMs) OpenAlex Paper Abel Ureste, Hyungbae Park et al. Mar 21 053 DeepSeek-Rl Family Large Language Models in the Tasks of Identification, Classification, and Detection of Vulnerabilities from the CWE Top 25 List OpenAlex Paper V. V. Shvyrov, D. A. Kapustin et al. Mar 18 054 Dialect-Agnostic SQL Parsing via LLM-Based Segmentation OpenAlex Paper Junwen An, Kabilan Mahathevan et al. Mar 17 055 Sadhana Programming Language v1.0 — A Meaning-First, Order-Free, Time-Latent Programming Language OpenAlex Paper Manish Kumar Parihar Mar 3 056 Sadhana Programming Language v1.0 — A Meaning-First, Order-Free, Time-Latent Programming Language OpenAlex Paper Manish Kumar Parihar Mar 3 057 Bridging AI and software security: A comparative vulnerability assessment of LLM agent deployment paradigms OpenAlex Paper Tarek Gasmi, Ramzi Guesmi et al. Feb 11 058 🖥 Zomro Coupon Code 2026 [zomro_433382] – 70% OFF Hosting Plans OpenAlex Paper shashank Feb 10 059 🖥 Zomro Coupon Code 2026 [zomro_433382] – 70% OFF Hosting Plans OpenAlex Paper shashank Feb 10 060 Fix Pattern-Aware Vulnerability Patch Generation via In-Context Learning OpenAlex Paper Miaomiao Shao, Yuxin Ding et al. Feb 9