PaperScope
LIVE · 2026-09-23 05:40 UTC

security 14 papers this week · +275% WoW

papers mentioning "security" in title/abstract · 30d window

Latestcs.CLcs.LGcs.AIcs.CV

Mentions per Day (30d)

Latest Papers

#TitleAuthorsCatDate
1Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware ScreenOm Nepal, Sushant Aryal, Oluseyi Olukola +1cs.SE2026-09-22
2Diffusion-Induced Spatial Attention Overlapping Community DetectionKosti Koistinen, Vesa Kuikka, Joni Herttuainen +3cs.SI2026-09-22
3Evaluating the Semantic-to-Geometric Gap in Adversarial Defenses Against Vision-Language Model-Based PlagiarismChristopher Burger, Christina Trotter, Joseph Carlisle +1cs.CV2026-09-22
#4From Alignment to Access Control: A Framework for GenAI Policy EnforcementNathalie Baracaldocs.CR2026-09-22
#5Unlocking Cross-Scenario Physical Layer Security: A Mixture-of-Experts Framework with Generative Diffusion ModelsXiao Tang, Tong Hui, Chao Shen +4eess.SP2026-09-22
#6HYDRA: Proactive Android Malware Drift Adaptation via Hierarchical Graph Contrastive LearningHan Chen, Hanchen Wang, Hongmei Chen +3cs.CR2026-09-22
#7On the security and privacy of LLMs in MobilityMauro Conti, Lorenzo Perinello, Umberto Salviatics.CR2026-09-22
#8Toward Responsible AI-Augmented Cyber Defense: Pattern Recognition, Defense-in-Depth, and the Case for Human-AI CollaborationMustafa S. Aljumaily, Hayder Kareem Abed, Nawar S. Alseelawics.CR2026-09-22
#9LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion ModelsJin Wei, Rundong Li, Ruihao Yang +10cs.CR2026-09-22
#10RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific RefutationAbdullahil Kafi, Alvi Ataur Khalilcs.AI2026-09-21
#11SSP-Bench: A Hybrid Data Generation Framework for Safety, Security, and Privacy EvaluationFatih Deniz, Yazan Boshmaf, Issa Khalilcs.CR2026-09-21
#12Reasoning Topology Matters: A Controlled Study of LLM-Based Cybersecurity AnalysisJiling Zhou, Aisvarya Adeseye, Antti Hakkala +2cs.CR2026-09-21
#13Offline Reinforcement Learning for Distribution-Grid ProtectionJulian Oelhaf, Alexander Luce, Christian Bergler +2eess.SY2026-09-21
#14Trust in Edge-Enabled IoT Security: Features, Challenges and Research DirectionsEsin Ece Aydın, Şerif Bahtiyar, Gürkan Gürcs.CR2026-09-21
#15DUMA-Bench: A Dual-Control Multi-Agent Benchmark for Evaluating LLM Agent SecurityIvan Aleksandrov, German Kochnev, Sabrina Sadiekh +1cs.AI2026-09-21
#16Beyond Predictable Paths: Redefining AI Security Incident Reporting for AgentsAnastasia Pustozerova, Eugene Bagdasarian, Luca Beurer-Kellner +22cs.CR2026-09-21
#17ActGov: Governing LLM Agent Actions via Policy-Constrained ValidationKaiyuan Zhang, Yuke Peng, Ke Jiang +1cs.CR2026-09-21
#18Climate Variability Modulates the Impact of Price Spikes on Food InsecurityJordi Cerdà-Bautista, Vasileios Sitokonstantinou, Homer Durand +3cs.LG2026-09-21
#19Credit Access is Associated with Improved Food Security in the Horn of AfricaJordi Cerdà-Bautista, Vasileios Sitokonstantinou, José Manuel Veiga López-Peña +3cs.LG2026-09-21
#20Temporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware DetectionMd. Asif Sajeed, Md. Nazrul Islam Mondal, Md Ashraful Hossen Akashcs.CR2026-09-21
#21High-Dimensional Online Change Point Detection with Adaptive Thresholding and InterpretabilitySven Jacob, Bardh Prenkaj, Weijia Shao +1cs.LG2026-09-21
#22Structured Decomposition for Reliable LLM-Generated Access Control PoliciesVatsal Gupta, Darshan Sreenivasamurthycs.AI2026-09-21
#23MobileCybench: Evaluating Agent Vulnerability Discovery via Executable ProbesAndy K. Zhang, Ava Huang, Joey Ji +21cs.CR2026-09-21
#24Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open ChallengesHeewon Baek, Alsharif Abuadbba, Kristen Moore +2cs.CR2026-09-20
#25Financial Language Models as Applied Artificial Intelligence Systems for News-Based Trading under Market FrictionsKemal Kirtaccs.CL2026-09-20
#26When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating SystemsLi Zhang, Yang Sun, Jie Shics.CR2026-09-20
#27When Agentic Trust Crosses Organizational Boundaries: Structural Externalization and a Reference Model for Trust EvidenceHuafu Li, Jia Xiacs.CR2026-09-19
#28SelfOp: An Optimization Algorithm for Self-Improving Security AgentsSaad Ullah, Yigitcan Kaya, Christopher Kruegel +2cs.CR2026-09-19
#29MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory LearningChangyue Jiang, Jiayi Wang, Xin Wen +3cs.CR2026-09-19
#30Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM SystemsFayeq Jeelani Syed, Rehan Ahmad, Ali Al Bataineh +1cs.AI2026-09-19
#31From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference ImplementationJoas Antonio dos Santos Barbosacs.CR2026-09-19
#32ServeGuard: Verifiable, Bounded-Residual Confinement of Operator-Invisible Channels Without Revealing the Certified Read FactorDominik Dahlem, Rui Vieiracs.CR2026-09-18
#33HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model InferenceByeongseo Min, Yongwoo Lee, Young-Sik Kim +1cs.CR2026-09-18
#34Offline Multimodal Large Language Models for Decision Support in Air OperationsJoao P. A. Dantas, Jelton A. Cunha, Gabriel Dietzschcs.AI2026-09-18
#35CESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT DevicesWenquan Zhou, An Wang, Jing Liang +4cs.CR2026-09-18
#36Fast And Accurate Text Content File Type IdentificationManu Nandan, Michael Brautbar, Edward Raffcs.LG2026-09-18
#37Identifying Security Platform Product Abuse with Machine LearningShaefer Drew, Michael Brautbar, Paul Knight +6cs.CR2026-09-18
#38RISC-V and machine learning: a surveyShriman Keshri, Apparna Singh, Chinmaya Kumar Palo +2cs.LG2026-09-17
#39Compact Vision Models for Iris Presentation Attack Detection under Presentation Attack Instrument Shift and Environmental DegradationAthanasios Angelakis, Marta Gomez-Barrerocs.CV2026-09-17
#40A Proposal for an Agentic AI Architecture to Support Multi-Domain Decision-Making in the Brazilian Armed ForcesGioliano de Oliveira Braga, Sidnei Barbieri, Ágney Lopes Roth Ferraz +2cs.AI2026-09-17
#41Robust Workflow Generation via Adversarial Learning for Audio Deepfake DetectionXiang Li, Pin-Yu Chen, Wenqi Weics.SD2026-09-17
#42AURA: Adaptive Uncertainty-Routed Analysis for Email Threat DetectionOmran Berjawi, Walid fahs, Rida Khatouncs.LG2026-09-17
#43Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression ProxiesHang Xiao, Chuhong Xu, Kainan Zhou +2cs.CR2026-09-17
#44Federated Learning Framework for Privacy-Preserving Kidney Stone DetectionNajiyya Younas, Omar Abdulkader, Yaser Ali Shah +3cs.CV2026-09-17
#45ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware AnalyzersHyeongjun Choi, Wonyoung Jung, Haehoon Seo +1cs.CR2026-09-17
#46SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading SchemesMengxiao Wang, Nitesh Saxenacs.CR2026-09-17
#47Closed-World Resolution Against Tool Hallucination in LLM AgentsLaxmipriya Ganesh Iyercs.AI2026-09-16
#48Efficient Nash Equilibrium Computation for Cybersecurity GamesMichael Lanier, David Farmer, Yevgeniy Vorobeychikcs.GT2026-09-16
#49MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic OutputsAlbert Wu, Nicholas Roberts, Tzu-Heng Huang +5cs.AI2026-09-16
#50ReDIL-GNN: Resynthesis Domain Incremental Learning for Circuit Graph Neural NetworksRupesh Raj Karn, Johann Knechtel, Ozgur Sinanoglucs.LG2026-09-16

all trends · matching is case-insensitive substring after tokenization