✨Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
📝 Summary:
This paper introduces the first systematic benchmark for evaluating knowledge-extraction attacks and defenses on Retrieval-Augmented Generation systems. It standardizes testing across diverse models and strategies to enable comparable evaluation and help build privacy-preserving RAG.
🔹 Publication Date: Published on Feb 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.09319
• PDF: https://arxiv.org/pdf/2602.09319
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#RAG #KnowledgeExtraction #Cybersecurity #AIPrivacy #Benchmarking
📝 Summary:
This paper introduces the first systematic benchmark for evaluating knowledge-extraction attacks and defenses on Retrieval-Augmented Generation systems. It standardizes testing across diverse models and strategies to enable comparable evaluation and help build privacy-preserving RAG.
🔹 Publication Date: Published on Feb 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.09319
• PDF: https://arxiv.org/pdf/2602.09319
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#RAG #KnowledgeExtraction #Cybersecurity #AIPrivacy #Benchmarking
✨NESSiE: The Necessary Safety Benchmark -- Identifying Errors that should not Exist
📝 Summary:
NESSiE is a new safety benchmark revealing basic security vulnerabilities in large language models with simple tests. Even state-of-the-art models fail these necessary safety checks, showing a bias towards helpfulness over safety and underscoring deployment risks.
🔹 Publication Date: Published on Feb 18
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.16756
• PDF: https://arxiv.org/pdf/2602.16756
• Project Page: https://huggingface.co/datasets/JByale/NESSiE
• Github: https://github.com/JohannesBertram/NESSiE
✨ Datasets citing this paper:
• https://huggingface.co/datasets/JByale/NESSiE
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AISafety #LLM #Cybersecurity #AIethics #AIResearch
📝 Summary:
NESSiE is a new safety benchmark revealing basic security vulnerabilities in large language models with simple tests. Even state-of-the-art models fail these necessary safety checks, showing a bias towards helpfulness over safety and underscoring deployment risks.
🔹 Publication Date: Published on Feb 18
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.16756
• PDF: https://arxiv.org/pdf/2602.16756
• Project Page: https://huggingface.co/datasets/JByale/NESSiE
• Github: https://github.com/JohannesBertram/NESSiE
✨ Datasets citing this paper:
• https://huggingface.co/datasets/JByale/NESSiE
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AISafety #LLM #Cybersecurity #AIethics #AIResearch
❤1
✨SlowBA: An efficiency backdoor attack towards VLM-based GUI agents
📝 Summary:
SlowBA is a novel backdoor attack targeting the response latency of VLM-based GUI agents. It induces excessively long reasoning chains using realistic pop-up window triggers, significantly increasing response length and latency while maintaining task accuracy. This reveals a new security vulnerab...
🔹 Publication Date: Published on Mar 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.08316
• PDF: https://arxiv.org/pdf/2603.08316
• Github: https://github.com/tu-tuing/SlowBA
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#BackdoorAttack #AISecurity #VLM #GUIagents #Cybersecurity
📝 Summary:
SlowBA is a novel backdoor attack targeting the response latency of VLM-based GUI agents. It induces excessively long reasoning chains using realistic pop-up window triggers, significantly increasing response length and latency while maintaining task accuracy. This reveals a new security vulnerab...
🔹 Publication Date: Published on Mar 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.08316
• PDF: https://arxiv.org/pdf/2603.08316
• Github: https://github.com/tu-tuing/SlowBA
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#BackdoorAttack #AISecurity #VLM #GUIagents #Cybersecurity
✨Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates
📝 Summary:
Session Risk Memory SRM enhances authorization by evaluating agent behavior over time, addressing distributed attacks. It uses semantic centroids and risk accumulation to achieve perfect detection with zero false positives, eliminating issues with stateless systems.
🔹 Publication Date: Published on Mar 22
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22350
• PDF: https://arxiv.org/pdf/2603.22350
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#Cybersecurity #TemporalAuthorization #DistributedSystems #BehavioralAnalytics #RiskDetection
📝 Summary:
Session Risk Memory SRM enhances authorization by evaluating agent behavior over time, addressing distributed attacks. It uses semantic centroids and risk accumulation to achieve perfect detection with zero false positives, eliminating issues with stateless systems.
🔹 Publication Date: Published on Mar 22
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22350
• PDF: https://arxiv.org/pdf/2603.22350
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#Cybersecurity #TemporalAuthorization #DistributedSystems #BehavioralAnalytics #RiskDetection
✨ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
📝 Summary:
OpenClaw agents face critical security vulnerabilities due to extensive operational privileges. ClawKeeper provides comprehensive real-time protection using skill-based, plugin-based, and novel watcher-based mechanisms for state verification and intervention.
🔹 Publication Date: Published on Mar 25
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.24414
• PDF: https://arxiv.org/pdf/2603.24414
• Project Page: https://huggingface.co/datasets/xunyoyo/clawkeeper
• Github: https://github.com/SafeAI-Lab-X/ClawKeeper
✨ Datasets citing this paper:
• https://huggingface.co/datasets/xunyoyo/clawkeeper
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AISafety #AgentSecurity #AIagents #Cybersecurity #AIResearch
📝 Summary:
OpenClaw agents face critical security vulnerabilities due to extensive operational privileges. ClawKeeper provides comprehensive real-time protection using skill-based, plugin-based, and novel watcher-based mechanisms for state verification and intervention.
🔹 Publication Date: Published on Mar 25
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.24414
• PDF: https://arxiv.org/pdf/2603.24414
• Project Page: https://huggingface.co/datasets/xunyoyo/clawkeeper
• Github: https://github.com/SafeAI-Lab-X/ClawKeeper
✨ Datasets citing this paper:
• https://huggingface.co/datasets/xunyoyo/clawkeeper
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AISafety #AgentSecurity #AIagents #Cybersecurity #AIResearch
✨Do Phone-Use Agents Respect Your Privacy?
📝 Summary:
This paper introduces MyPhoneBench, a framework to evaluate phone agents' privacy behavior. It found agents often over-share optional data, indicating current success metrics overestimate their deployment readiness due to privacy failures.
🔹 Publication Date: Published on Apr 1
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.00986
• PDF: https://arxiv.org/pdf/2604.00986
• Github: https://github.com/FreedomIntelligence/MyPhoneBench
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#PhoneAgents #DataPrivacy #AI #PrivacyResearch #Cybersecurity
📝 Summary:
This paper introduces MyPhoneBench, a framework to evaluate phone agents' privacy behavior. It found agents often over-share optional data, indicating current success metrics overestimate their deployment readiness due to privacy failures.
🔹 Publication Date: Published on Apr 1
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.00986
• PDF: https://arxiv.org/pdf/2604.00986
• Github: https://github.com/FreedomIntelligence/MyPhoneBench
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#PhoneAgents #DataPrivacy #AI #PrivacyResearch #Cybersecurity
❤1
✨AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration
📝 Summary:
AutoMIA is an agentic framework that automates membership inference attacks. It dynamically generates and refines attack strategies via self-exploration and closed-loop evaluation. This approach consistently outperforms static methods by eliminating manual feature engineering and improving adapta...
🔹 Publication Date: Published on Apr 1
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01014
• PDF: https://arxiv.org/pdf/2604.01014
• Github: https://github.com/amiya-special/AutoMIA
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#MembershipInference #MLSecurity #Cybersecurity #AI #DataPrivacy
📝 Summary:
AutoMIA is an agentic framework that automates membership inference attacks. It dynamically generates and refines attack strategies via self-exploration and closed-loop evaluation. This approach consistently outperforms static methods by eliminating manual feature engineering and improving adapta...
🔹 Publication Date: Published on Apr 1
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01014
• PDF: https://arxiv.org/pdf/2604.01014
• Github: https://github.com/amiya-special/AutoMIA
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#MembershipInference #MLSecurity #Cybersecurity #AI #DataPrivacy
✨Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
📝 Summary:
Tex3D is the first framework optimizing 3D adversarial textures to attack vision-language-action models. It significantly degrades robotic manipulation performance in real-world settings, revealing critical vulnerabilities.
🔹 Publication Date: Published on Apr 2
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01618
• PDF: https://arxiv.org/pdf/2604.01618
• Project Page: https://vla-attack.github.io/tex3d/
• Github: https://github.com/vla-attack/tex3d
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AdversarialAI #Robotics #VLAmodels #Cybersecurity #ComputerVision
📝 Summary:
Tex3D is the first framework optimizing 3D adversarial textures to attack vision-language-action models. It significantly degrades robotic manipulation performance in real-world settings, revealing critical vulnerabilities.
🔹 Publication Date: Published on Apr 2
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01618
• PDF: https://arxiv.org/pdf/2604.01618
• Project Page: https://vla-attack.github.io/tex3d/
• Github: https://github.com/vla-attack/tex3d
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AdversarialAI #Robotics #VLAmodels #Cybersecurity #ComputerVision
✨AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks
📝 Summary:
AgentSocialBench evaluates privacy in human-centered agentic social networks. It finds multi-agent coordination leads to persistent leakage and an abstraction paradox, showing current LLM agents are insufficient for privacy preservation. New mechanisms are required.
🔹 Publication Date: Published on Apr 1
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01487
• PDF: https://arxiv.org/pdf/2604.01487
• Project Page: https://agent-social-bench.github.io/
• Github: https://github.com/kingofspace0wzz/agentsocialbench
✨ Datasets citing this paper:
• https://huggingface.co/datasets/kingofspace0wzz/AgentSocialBench
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AgenticAI #PrivacyRisks #LLMAgents #SocialNetworks #Cybersecurity
📝 Summary:
AgentSocialBench evaluates privacy in human-centered agentic social networks. It finds multi-agent coordination leads to persistent leakage and an abstraction paradox, showing current LLM agents are insufficient for privacy preservation. New mechanisms are required.
🔹 Publication Date: Published on Apr 1
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01487
• PDF: https://arxiv.org/pdf/2604.01487
• Project Page: https://agent-social-bench.github.io/
• Github: https://github.com/kingofspace0wzz/agentsocialbench
✨ Datasets citing this paper:
• https://huggingface.co/datasets/kingofspace0wzz/AgentSocialBench
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AgenticAI #PrivacyRisks #LLMAgents #SocialNetworks #Cybersecurity
✨Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
📝 Summary:
A real-world safety analysis of the personal AI agent OpenClaw reveals significant vulnerabilities due to its broad system access. Attacks targeting its Capability, Identity, or Knowledge CIK dimensions drastically increase success rates, and current defenses are insufficient, indicating inherent...
🔹 Publication Date: Published on Apr 6
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.04759
• PDF: https://arxiv.org/pdf/2604.04759
• Project Page: https://ucsc-vlaa.github.io/CIK-Bench/
• Github: https://github.com/UCSC-VLAA/CIK-Bench
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AISafety #Cybersecurity #AIAgents #Vulnerability #AIsecurity
📝 Summary:
A real-world safety analysis of the personal AI agent OpenClaw reveals significant vulnerabilities due to its broad system access. Attacks targeting its Capability, Identity, or Knowledge CIK dimensions drastically increase success rates, and current defenses are insufficient, indicating inherent...
🔹 Publication Date: Published on Apr 6
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.04759
• PDF: https://arxiv.org/pdf/2604.04759
• Project Page: https://ucsc-vlaa.github.io/CIK-Bench/
• Github: https://github.com/UCSC-VLAA/CIK-Bench
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AISafety #Cybersecurity #AIAgents #Vulnerability #AIsecurity
👍1
🔥 Free IT Cert Resources – Grab Them While They're Hot!
🌈SPOTO just dropped a bunch of 100% free study kits for 2026 – covering #Cisco, #AWS, #PMP, #AI, #Python, #Excel, and #Cybersecurity
💥No signup traps, no hidden fees – just click and download.
📘 FREE Cert E‑Book → https://bit.ly/4wkiLAT
🪜 Online FREE Course → https://bit.ly/4vHFJSz
☁️ FREE AI Materials → https://bit.ly/4wdu7X6
📊 Cloud Study Guide → https://bit.ly/4y0HyeW
🧠 Free Mock Exam → https://bit.ly/4ff8jos
Tag a friend who's also on this journey – Get certified together! 💪
🌐 Join the community: https://chat.whatsapp.com/FmbIbbqm2QhKglVpVTSH4d/
📲 Need personalized help? → https://wa.link/6k7042
🌈SPOTO just dropped a bunch of 100% free study kits for 2026 – covering #Cisco, #AWS, #PMP, #AI, #Python, #Excel, and #Cybersecurity
💥No signup traps, no hidden fees – just click and download.
📘 FREE Cert E‑Book → https://bit.ly/4wkiLAT
🪜 Online FREE Course → https://bit.ly/4vHFJSz
☁️ FREE AI Materials → https://bit.ly/4wdu7X6
📊 Cloud Study Guide → https://bit.ly/4y0HyeW
🧠 Free Mock Exam → https://bit.ly/4ff8jos
Tag a friend who's also on this journey – Get certified together! 💪
🌐 Join the community: https://chat.whatsapp.com/FmbIbbqm2QhKglVpVTSH4d/
📲 Need personalized help? → https://wa.link/6k7042
❤1
🔥 Free IT Cert Resources – Grab Them While They're Hot!
🌈SPOTO just dropped a bunch of 100% free study kits for 2026 – covering #Cisco, #AWS, #PMP, #AI, #Python, #Excel, and #Cybersecurity
💥No signup traps, no hidden fees – just click and download.
📘 FREE Cert E‑Book → https://bit.ly/4wkiLAT
🪜 Online FREE Course → https://bit.ly/4vHFJSz
☁️ FREE AI Materials → https://bit.ly/4wdu7X6
📊 Cloud Study Guide → https://bit.ly/4y0HyeW
🧠 Free Mock Exam → https://bit.ly/4ff8jos
Tag a friend who's also on this journey – Get certified together! 💪
🌐 Join the community: https://chat.whatsapp.com/FmbIbbqm2QhKglVpVTSH4d/
📲 Need personalized help? → https://wa.link/6k7042
🌈SPOTO just dropped a bunch of 100% free study kits for 2026 – covering #Cisco, #AWS, #PMP, #AI, #Python, #Excel, and #Cybersecurity
💥No signup traps, no hidden fees – just click and download.
📘 FREE Cert E‑Book → https://bit.ly/4wkiLAT
🪜 Online FREE Course → https://bit.ly/4vHFJSz
☁️ FREE AI Materials → https://bit.ly/4wdu7X6
📊 Cloud Study Guide → https://bit.ly/4y0HyeW
🧠 Free Mock Exam → https://bit.ly/4ff8jos
Tag a friend who's also on this journey – Get certified together! 💪
🌐 Join the community: https://chat.whatsapp.com/FmbIbbqm2QhKglVpVTSH4d/
📲 Need personalized help? → https://wa.link/6k7042