Security Teams Overlook AI-Driven Threats in Cloud Risk Management
Stay ahead of the threats: are you managing cloud risk effectively, or is it still siloed and vulnerable to AI-driven attacks? Recent research from Google Threat Intelligence Group reveals a new wave of AI-augmented operations that are scaling and accelerating compromises.
#CloudRiskManagement #AidrivenThreats #AdversarialAi #AiaugmentedOperations #GoogleThreatIntelligenceGroup
AI-Driven Attacks Infiltrate Cloud Environments
Stay ahead of the threats: as AI-driven attacks infiltrate cloud environments, it's crucial to adopt a proactive, holistic approach to risk reduction and protect your critical assets and data. Google Cloud and XM Cyber warn that understanding how attackers move laterally throughout your network is key to safeguarding against emerging AI-drivenβ¦
#AdversarialAi #AidrivenAttacks #CloudSecurity #EmergingThreats #GoogleCloud
π¨ Introducing the AI Security Village at BSides Luxembourg 2026! π¨
π§ π€ ππ π¦πππ¨π₯ππ§π¬ π©ππππππ β π§ππππ‘ππππ π§π₯πππ‘ππ‘π & ππ π£πππ ππ‘π§ππ§ππ’π‘ (2-Day Deep Dive) β π£ππ₯π§π π¦ππ¨πππ & π‘ππππ₯ππ¨π‘ π₯πππππ£ππππ βοΈπ₯
π§πππ¦ ππ¦π‘βπ§ ππ¨π¦π§ ππ‘π’π§πππ₯ π§π₯πππ. π§πππ¦ ππ¦ πͺπππ₯π π§πππ’π₯π¬ π πππ§π¦ πππ‘ππ¦-π’π‘ ππ π¦πππ¨π₯ππ§π¬.
The AI Security Village brings a full 2-day immersive technical experience, diving deep into real-world implementation of AI security. From adversarial machine learning to securing agentic systems and LLM architectures, this village is designed for practitioners who want to go beyond concepts and actually build, break, and secure AI systems.
Expect intensive, hands-on sessions, practical techniques, and real-world scenarios covering how modern AI systems are attackedβand how to defend them effectively.
Parth Shukla is a Senior Security Researcher specializing in AI Security and Adversarial Machine Learning. With a strong offensive security background, his work focuses on securing agentic systems and LLM architectures, bridging the gap between traditional AppSec and emerging AI-driven risks.
Nagarjun Rallapalli is involved in advancing AI security initiatives and contributes to building and testing secure AI systems.
π
Conference Dates: 6β8 May 2026 | 09:00β18:00
π 14, Porte de France, Esch-sur-Alzette, Luxembourg
ποΈ Tickets: https://2026.bsides.lu/tickets/
π
Schedule Link: https://pretalx.com/bsidesluxembourg-2026/schedule/
#BSidesLuxembourg2026 #AISecurityVillage #AISecurity #AdversarialAI #LLMSecurity #CyberSecurity #RedTeam #AI
Another talk announcement for BSides Luxembourg!
π§ π» π§πππ π§π’ π π¦ππππ: ππ«π£ππ’ππ§ππ‘π ππ ππππ‘π§π¦ ππ‘ π₯πππ π§ππ π β Parth Shukla β‘
AI agents are no longer just chatbotsβthey can execute commands, access files, and interact with real systems. But what if an attacker could control all of thatβ¦ just by talking?
This talk reveals a real-world vulnerability where full system command execution was achieved through natural language interaction alone. From reconnaissance to bypassing safeguards using jailbreak techniques, this session shows how AI agents can become unintended attack proxiesβno exploits, no credentials, just conversation.
Parth Shukla is a Senior Security Researcher specializing in AI Security and Adversarial Machine Learning, focusing on securing agentic systems and uncovering real-world vulnerabilities in LLM-driven architectures.
π
Conference Dates: 6β8 May 2026 | 09:00β18:00
π 14, Porte de France, Esch-sur-Alzette, Luxembourg
ποΈ Tickets: https://2026.bsides.lu/tickets/
π Schedule Link: https://pretalx.com/bsidesluxembourg-2026/schedule/
#BSidesLuxembourg2026 #AISecurity #LLM #AgenticAI #CyberSecurity #AppSec #AdversarialAI
This ' #antiAI content' that reads exactly like bad #LLM output on a gradient that looks like a 90s sticker book had a stroke. The snake isn't just eating its own tail, it's leaving a five-star review of the experience.
It won't work because scrapers don't care about your CSS. The text is still plaintext in the HTML. The gibberish doesn't poison anything, models already train on billions of tokens of garbage and route around it. And if your adversarial content is indistinguishable from the thing you're fighting, you're just contributing to the slop pile for free.
#adversarialAi not
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs
#HackerNews #DigitalRedQueen #AdversarialAI #CoreWar #LLMs #TechInnovation #Cybersecurity
Analyst207
Sudhanshu Shekhar
BSidesLuxembourg
WulfyβSpeaker to the machines
Bob Carver
jpmellojr
Hacker News