talks

Jun 22, 2026

• papers
• talks
• observability
• opentelemetry
• detection-engineering
• elastic

Jun 02, 2026

• papers
• talks
• vendor-evaluation
• capability-framework
• configure-buy-build

Jun 02, 2026

• papers
• talks
• agentic-soc
• salesforce
• supervisor-worker
• digital-teammates
• defense-in-depth

Jun 02, 2026

• papers
• talks
• agentic-soc
• evaluation
• meta

Jun 02, 2026

• papers
• talks
• threat-intelligence
• knowledge-graph
• osint
• palo-alto-networks

Jun 02, 2026

• papers
• talks
• detection-engineering
• prompt-injection
• yara
• sec-of-ai
• ai-in-sec-defense

Jun 02, 2026

• papers
• talks
• agentic-soc
• post-training
• sft
• grpo
• open-weights
• aws

Jun 02, 2026

• papers
• talks
• conference
• agentic-ai
• prompt-injection
• red-teaming
• vulnerability-discovery
• observability
• governance
• mcp
• browser-agents

May 26, 2026

• papers
• talks
• prompt-injection
• threat-intelligence
• differential-privacy
• detection-engineering
• sec-of-ai
• ai-in-sec-defense

May 26, 2026

• papers
• talks
• agentic-soc
• dfir
• mcp
• autonomous-adversaries
• ai-in-sec-defense

May 25, 2026

• papers
• talks
• agentic-soc
• threat-hunting
• ai-in-sec-defense

May 25, 2026

• papers
• talks
• agentic-soc
• detection-engineering
• deception
• ai-in-sec-defense

May 25, 2026

• papers
• talks
• agentic-soc
• evaluation
• benchmarks
• ai-in-sec-defense

May 25, 2026

• papers
• talks
• agentic-soc
• incident-response
• supply-chain
• ai-in-sec-defense

May 03, 2026

• papers
• talks
• agentic-ai
• observability
• behavioral-anomaly-detection
• salesforce
• agentforce
• soc
• unprompted-2026

May 03, 2026

• papers
• talks
• mcp-security
• memory-isolation
• capability-bounding
• agentic-ai
• observability
• prompt-injection
• dropbox
• unprompted-2026

May 03, 2026

• papers
• talks
• capability-based-authorization
• warrants
• delegation
• multi-agent-security
• prompt-injection-containment
• macaroons
• ucan
• cedar
• camel
• tenuo
• unprompted-2026

May 03, 2026

• papers
• talks
• mechanistic-interpretability
• glass-box-security
• behavior-based-detection
• latent-space
• agent-observability
• detection-engineering
• starseer
• unprompted-2026

May 03, 2026

• papers
• talks
• production-agents
• threat-modeling-agent
• security-routing-agent
• llm-as-a-judge
• evaluation-pipeline
• multi-agent-architecture
• human-in-the-loop
• hallucination-mitigation
• stripe
• unprompted-2026
• 1
• 2

May 03, 2026

• papers
• talks
• cedar
• coding-agents
• reference-monitor
• policy-engine
• trajectory-events
• information-flow-control
• lethal-trifecta
• hooks
• open-source
• unprompted-2026

May 03, 2026

• papers
• talks
• prompt-injection
• lethal-trifecta
• hitl
• workspace-security
• google

May 03, 2026

• papers
• talks
• prompt-injection
• agentic-ai
• red-teaming
• attack-patterns
• c2
• promptware
• unprompted-2026

May 02, 2026

• papers
• talks
• prompt-injection
• lethal-trifecta
• egress-control
• mcp-security
• human-in-the-loop
• tool-annotations
• stripe
• unprompted-2026

May 01, 2026

• papers
• talks
• gartner
• agentic-ai
• governance
• operating-model
• cio-playbook

Apr 30, 2026

• papers
• talks
• prompt-injection
• rag
• agentic-ai
• red-teaming
• defense-in-depth