The heart of the Rays batting order is hitting .100 with RISP this postseason; Cleveland is hitting .273. In fact, the only team doing worse than the Rays that hasn't been eliminated already? The Dodgers (0‑for‑8).
October 14, 2026 at 5:04 PM
The heart of the Rays batting order is hitting .100 with RISP this postseason; Cleveland is hitting .273. In fact, the only team doing worse than the Rays that hasn't been eliminated already? The Dodgers (0‑for‑8).
Benlong Wu, Guoqiang Chen, Kejiang Chen, Xiuwei Shang, Jiapeng Han, Yanru He, Weiming Zhang, Nenghai Yu
AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?
https://arxiv.org/abs/2411.01236
AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?
https://arxiv.org/abs/2411.01236
November 5, 2024 at 5:01 AM
Benlong Wu, Guoqiang Chen, Kejiang Chen, Xiuwei Shang, Jiapeng Han, Yanru He, Weiming Zhang, Nenghai Yu
AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?
https://arxiv.org/abs/2411.01236
AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?
https://arxiv.org/abs/2411.01236
Pics from the Autoptic Festival 2024. 🎉🎉🎉
www.patreon.com/posts/autopt...
www.patreon.com/posts/autopt...
Autoptic Festival 2024 | Jim Keefe
Get more from Jim Keefe on Patreon
www.patreon.com
August 18, 2024 at 4:20 PM
Pics from the Autoptic Festival 2024. 🎉🎉🎉
www.patreon.com/posts/autopt...
www.patreon.com/posts/autopt...
restricting adaptive improvement of PT strategies. To address these limitations, we propose a knowledge-informed self-reflective PT framework powered by LLMs, called RefPentester, which is an AutoPT framework designed to assist human operators in [4/7 of https://arxiv.org/abs/2505.07089v1]
May 13, 2025 at 5:59 AM
restricting adaptive improvement of PT strategies. To address these limitations, we propose a knowledge-informed self-reflective PT framework powered by LLMs, called RefPentester, which is an AutoPT framework designed to assist human operators in [4/7 of https://arxiv.org/abs/2505.07089v1]
by leveraging the intrinsic knowledge of LLMs. However, existing LLM-based AutoPT frameworks often underperform compared to human experts in challenging tasks for several reasons: the imbalanced knowledge used in LLM training, short-sighted planning [2/7 of https://arxiv.org/abs/2505.07089v1]
May 13, 2025 at 5:59 AM
by leveraging the intrinsic knowledge of LLMs. However, existing LLM-based AutoPT frameworks often underperform compared to human experts in challenging tasks for several reasons: the imbalanced knowledge used in LLM training, short-sighted planning [2/7 of https://arxiv.org/abs/2505.07089v1]
arXiv:2505.07089v1 Announce Type: new
Abstract: Automated penetration testing (AutoPT) powered by large language models (LLMs) has gained attention for its ability to automate ethical hacking processes and identify vulnerabilities in target systems [1/7 of https://arxiv.org/abs/2505.07089v1]
Abstract: Automated penetration testing (AutoPT) powered by large language models (LLMs) has gained attention for its ability to automate ethical hacking processes and identify vulnerabilities in target systems [1/7 of https://arxiv.org/abs/2505.07089v1]
May 13, 2025 at 5:59 AM
arXiv:2505.07089v1 Announce Type: new
Abstract: Automated penetration testing (AutoPT) powered by large language models (LLMs) has gained attention for its ability to automate ethical hacking processes and identify vulnerabilities in target systems [1/7 of https://arxiv.org/abs/2505.07089v1]
Abstract: Automated penetration testing (AutoPT) powered by large language models (LLMs) has gained attention for its ability to automate ethical hacking processes and identify vulnerabilities in target systems [1/7 of https://arxiv.org/abs/2505.07089v1]
四川大學；清華大學等：黑客還是幻覺？基於大語言模型的自動化滲透測試全面分析
四川大學；清華大學等：黑客還是幻覺？基於大語言模型的自動化滲透測試全面分析
本研究首次針對LLM驅動的AutoPT框架進行知識系統化分析，並開展全面而深入的大規模實證評估，旨在釐清當前技術真實的能力邊界，併為後續研究提供參考。
www.headline01.com
April 13, 2026 at 10:03 AM
四川大學；清華大學等：黑客還是幻覺？基於大語言模型的自動化滲透測試全面分析
arxiv.org/abs/2605.26195
CyberEvolver: self-evolving framework for Penetration Test.
#autopt #llm #cybersecurity
CyberEvolver: self-evolving framework for Penetration Test.
#autopt #llm #cybersecurity
May 27, 2026 at 8:12 AM
arxiv.org/abs/2605.26195
CyberEvolver: self-evolving framework for Penetration Test.
#autopt #llm #cybersecurity
CyberEvolver: self-evolving framework for Penetration Test.
#autopt #llm #cybersecurity
Quali sono i principali benchmarks per valutare le capacità cyber degli #llm? #autopt #bluteam #redteam
www.linkedin.com/pulse/benchm...
www.linkedin.com/pulse/benchm...
Benchmarks la valutazione delle capacità cyber dei modelli di intelligenza artificiale
Negli ultimi mesi l’interesse legato alle annunciate enormi capacità cyber dei modelli frontier come GPT‑5.5 e Claude Mythos Preview, ha stimolato la mia curiosità circa le metodologie di misurazione ...
www.linkedin.com
May 15, 2026 at 4:17 PM
Quali sono i principali benchmarks per valutare le capacità cyber degli #llm? #autopt #bluteam #redteam
www.linkedin.com/pulse/benchm...
www.linkedin.com/pulse/benchm...
L’autonomous pentesting #autopt non si gioca solo sulla forza del modello. La differenza la fanno controllo, memoria, orchestrazione e guardrail. In questo articolo spunti da due hackathon Tencent Cloud sull’evoluzione degli agenti autonomi per il penetration testing
www.linkedin.com/pulse/autono...
www.linkedin.com/pulse/autono...
Autonomous pentesting: il modello è nulla senza il controllo.
Negli ultimi mesi, una parte del dibattito sull’AI applicata alla cybersecurity si è concentrata soprattutto sulla potenza dei modelli. Ma leggendo l’analisi dei due Tencent Cloud Intelligent Penetrat...
https://www.linkedin.com/pulse/autonomous-pentesting-il-modello-è-nulla-senza-alfredo-terrone-4wcec/
May 11, 2026 at 4:29 PM
L’autonomous pentesting #autopt non si gioca solo sulla forza del modello. La differenza la fanno controllo, memoria, orchestrazione e guardrail. In questo articolo spunti da due hackathon Tencent Cloud sull’evoluzione degli agenti autonomi per il penetration testing
www.linkedin.com/pulse/autono...
www.linkedin.com/pulse/autono...
Cairn: A AI general-purpose state-space search engine, validated first on autonomous penetration testing.
github.com/oritera/Cairn
#autopt #llm
github.com/oritera/Cairn
#autopt #llm
May 11, 2026 at 11:04 AM
Cairn: A AI general-purpose state-space search engine, validated first on autonomous penetration testing.
github.com/oritera/Cairn
#autopt #llm
github.com/oritera/Cairn
#autopt #llm
Cosa ci dicono davvero i sistemi di Automated Penetration Testing basati su LLM linkedin.com/pulse/hacker...
Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing
Interessante pubblicazione: arxiv.org/abs/2604.05719
#Cyber #PT #AI #LLM #AutoPT
Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing
Interessante pubblicazione: arxiv.org/abs/2604.05719
#Cyber #PT #AI #LLM #AutoPT
"Hackers or Hallucinators?" — Cosa ci dicono davvero i sistemi di Automated Penetration Testing basati su LLM
Un team di oltre 15 ricercatori ha pubblicato il primo Systematization of Knowledge (SoK) sui framework di Penetration Testing Automatizzato basati su LLM (AutoPT) https://arxiv.org/abs/2604.
linkedin.com
April 18, 2026 at 12:12 PM
Cosa ci dicono davvero i sistemi di Automated Penetration Testing basati su LLM linkedin.com/pulse/hacker...
Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing
Interessante pubblicazione: arxiv.org/abs/2604.05719
#Cyber #PT #AI #LLM #AutoPT
Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing
Interessante pubblicazione: arxiv.org/abs/2604.05719
#Cyber #PT #AI #LLM #AutoPT