IA Crítica sem Filtro — "Você é burro, velho?"
Quer ver uma IA sem filtro que chama as coisas pelo nome? 😂👇
• O que acontece aqui:
- Uma versão crítica de IA age como um 'Senior' sem papas na língua — "Você é burro, velho?" 🤯
• Contexto e keywords:
- IA […]
[Original post on mastodon.social]
The Real State of Offensive Security: AI, Penetration Testing & The Road Ahead with Andrew Wilson Tom Eston interviews offensive AI researcher and PhD candidate Andrew Wilson, a former Bishop F...
#Analytics #& #Intelligence #Application […]
[Audio] [Original post on securityboulevard.com]
#Deep #Learning #Generative #Adversarial #Network #Machine #Learning #(ML) #Natural #Language #Generation
Origin | Interest | Match
Game-Theoretic Defenses for Adversarially Robust Conformal Prediction
Rui Luo, Jie Bao, Suqun Cao, Chuangyin Dang, Zhixin Zhou
Action editor: Mingming Gong
https://openreview.net/forum?id=SjsVobIlwL
#adversarial #adversarially #adversary
RT2I-Bench: Evaluating Robustness of Text-to-Image Systems Against Adversarial Attacks
Athanasios Glentis, Ioannis Tsaknakis, Jiangweizhi Peng et al.
Action editor: Dit-Yan Yeung
https://openreview.net/forum?id=ZUiWjEouSf
#adversarial #rt2i #t2i
Adversarial Vulnerability from On-Manifold Inseparability and Poor Off-Manifold Convergence
Rajdeep Haldar, Yue Xing, Qifan Song, Guang Lin
Action editor: Olivier Cappé
https://openreview.net/forum?id=pa90uRZATF
#adversarial #robustness #classification
Overcoming Open-Set Approaches to Adversarial Defense
Edgar Wilfred Jatho, Armon Barton, Matthew Wright, Patrick McClure
Action editor: Meisam Razaviyayn
https://openreview.net/forum?id=iuQ9r8VSIX
#adversarial #defenses #attacks
#resist with #adversarial #fashion, my favorite kind. The Coruscanti eat this up. Since we set the trend, we now have friends everywhere.
aiunpackedpod.substack.com/p/anti-ai-fa...
SoundnessBench: A Soundness Benchmark for Neural Network Verifiers
Xingjian Zhou, Keyi Shen, Andy Xu, Hongji Xu, Cho-Jui Hsieh, Huan Zhang, Zhouxing Shi
Action editor: Grigorios Chrysos
https://openreview.net/forum?id=UuYYldVLH3
#soundnessbench #adversarial #soundness
🤓 At BlackHat Asia in Singapore, I am running two advanced AI trainings with my friend Maxime Cousseau that go beyond slides and hype. You will build and break real AI systems!
🤖 Practical GenAI for CTI – 2 Days
Stop watching demos. Build real agentic […]
[Original post on infosec.exchange]
Inside Adversarial Reasoning: How AI Labs Are Teaching Models to Think by Fighting Themselves AI labs are embracing adversarial reasoning—pitting models against themselves through debate, self-pl...
#GenAIPro #adversarial #reasoning #AI #safety #AI #training […]
[Original post on webpronews.com]
Pluralistic: End of the line for video essays (07 Feb 2026) Today's links End of the line for video essays: America's worst copyright law keeps getting even worse. Hey look at this: Delight...
#Uncategorized #1201 #adversarial #interoperability […]
[Original post on pluralistic.net]
Pluralistic: End of the line for video essays (07 Feb 2026) Today's links End of the line for video essays: America's worst copyright law keeps getting even worse. Hey look at this: Delight...
#Uncategorized #1201 #adversarial #interoperability […]
[Original post on pluralistic.net]
Mirror Descent Policy Optimisation for Robust Constrained Markov Decision Processes
David Mark Bossens, Atsushi Nitanda
Action editor: Alberto Maria Metelli
https://openreview.net/forum?id=tmfdqtFUqO
#adversarial #robustness #optimise
A Pattern Language for Machine Learning Tasks
Benjamin Rodatz, Ian Fan, Tuomas Laakkonen et al.
Action editor: Stefano Teso
https://openreview.net/forum?id=IOianP0UHC
#adversarial #learners #tasks
Pluralistic: Threads' margin is the Eurostack's opportunity (30 Jan 2026) Today's links Threads' margin is the Eurostack's opportunity: Move fast and break kings. Hey look at th...
#Uncategorized #activitypub #ad-tech #adblock #adversarial #interoperability […]
[Original post on pluralistic.net]
AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving
Shuo Xing, Hongyuan Hua, Xiangbo Gao et al.
Action editor: Weijian Deng
https://openreview.net/forum?id=z2VZl6sH7T
#drivevlms #adversarial #trustworthiness
Черепаха-винтовка: как обмануть ИИ Ваша нейросеть уверенно распознаёт панду. Но стоит добавить несколько н...
#adversarial #machine #learning #нейросети #безопасность #ML #adversarial #attacks #защита #моделей #adversarial
Origin | Interest | Match
My latest book of AI red teaming is now online. This is my first self-published book on the topic of AI security.
zerooneeta.gumroad.com/l/mczwmg
#llm #ai #redteaming #adversarial #Aitesting #ebook
An Evolutionary Algorithm for Black-Box Adversarial Attack Against Explainable Methods
Phoenix Neale Williams, Jessica Schrouff, Lea Goetz
Action editor: Yingzhen Li
https://openreview.net/forum?id=MlUP5Euj6S
#adversarial #ai #xai
Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics
PANKAJ KUMAR, Subhankar Mishra
Action editor: Aditya Menon
https://openreview.net/forum?id=Bchvaaod6g
#robustness #nlp #adversarial
✨ This year I will teach two trainings at @blackhatevents Asia in April!
🧠 Practical GenAI for Threat Intel: Real World Agentic Workflows for Cyber Threat Intelligence (2 days)
Latest version of the course, with a strong focus on agent architectures […]
[Original post on infosec.exchange]
Improving Adversarial Training for Two-player Competitive Games via Episodic Reward Engineering
Siyuan Chen, Fuyuan Zhang, Zhuo Li et al.
Action editor: Tongzheng Ren
https://openreview.net/forum?id=z4XtJWJC9K
#adversarial #reward #rewards
Weakly Supervised Object Segmentation by Background Conditional Divergence
Hassan Baker, Matthew Emigh, Austin J. Brockmeier
Action editor: Mathieu Salzmann
https://openreview.net/forum?id=2JJZhfGvMW
#supervised #masking #adversarial
An Empirical Study of the Accuracy-Robustness Trade-off and Training Efficiency in Robust Self-Su...
Fatemeh Ghofrani, Mehdi Yaghouti, Pooyan Jamshidi
Action editor: Evan Shelhamer
https://openreview.net/forum?id=WTqHDiETg5
#adversarial #ssl #supervised
Adversarial Surrogate Risk Bounds for Binary Classification
Natalie Frank
Action editor: Han Bao
https://openreview.net/forum?id=Bay1cHLk7h
#adversarial #classifiers #risk
A Hierarchical Nearest Neighbour Approach to Contextual Bandits
Stephen Pasteris, Madeleine Dwyer, Chris Hicks, Vasilios Mavroudis
Action editor: Zheng Wen
https://openreview.net/forum?id=4bJMIrI5oX
#bandits #bandit #adversarial
Adversarial Robustness of Graph Transformers
Philipp Foth, Lukas Gosch, Simon Geisler, Leo Schwinn, Stephan Günnemann
Action editor: Xingchen Wan
https://openreview.net/forum?id=4xK0vjxTWL
#adversarial #attacks #vulnerability
You can buy this exploit on Etsy.
Hoodies that make cameras think you're a giraffe. Jackets covered in fake license plates. #Adversarial fashion is a #product category now.
Adversarial Bandits Against Arbitrary Strategies
Jung-hun Kim, Se-Young Yun
Action editor: Yaoliang Yu
https://openreview.net/forum?id=x4QrOh8uCs
#bandits #bandit #adversarial
