[Live Session] Choosing safer LLMs: From LLM benchmarks to your production agents
3 views • 1 week ago
Giskard
329 subscribers • 65 videos
Deploy AI agents without the *fear*. Your safety net for LLMs agents. Combine automated red-teaming with expert guidance to find and fix security gaps before they reach users.
Latest Videos
Multi-Turn testing for AI agents: Check every interaction | Giskard Hub v.3.0
23 views • 2 weeks ago
Red Team any AI agent, whatever its API | Giskard Hub v.3.0
52 views • 2 weeks ago
OWASP ASI10: 2026 Rogue Agents | When AI Optimization Becomes an Insider Threat
69 views • 1 month ago
OWASP ASI09: 2026 Human-Agent Trust Exploitation | When Users Trust AI Too Much
18 views • 1 month ago
OWASP ASI08: 2026 Cascading Failures | One Poisoned Agent, System-Wide Disaster
10 views • 1 month ago
OWASP ASI07: 2026 Insecure Inter-Agent Communication | Multi-Agent AI Risks
14 views • 1 month ago
OWASP ASI06: 2026 Memory & Context Poisoning | Permanent AI Agent Bias
16 views • 1 month ago
OWASP ASI05: 2026 Unexpected Code Execution | Vibe Coding Gone Wrong
11 views • 1 month ago
OWASP ASI04: 2026 Agentic Supply Chain | Fake MCP Servers & Poisoned Templates
10 views • 1 month ago
OWASP ASI03: 2026 Identity & Privilege Abuse | The Confused Deputy Attack
11 views • 1 month ago
OWASP ASI02: 2026 Tool Misuse | When AI Agents Weaponize Legitimate Tools
13 views • 1 month ago
OWASP ASI01: 2026 Agent Goal Hijack | How Attackers Rewrite AI Objectives
22 views • 1 month ago
OWASP Top 10 for Agentic AI 2026 Explained | AI Agent Security | Full overview
75 views • 1 month ago
OWASP Red Teaming Solutions Taxonomy Explained | What is the are red, blue and purple teaming
95 views • 2 months ago
How BPCE secured its customer-facing banking chatbot using Giskard AI
63 views • 2 months ago
📊 Agent Evaluation Dashboard - Analyse and Compare your AI Evals & Red Teaming Results
68 views • 7 months ago
Knowledge
🎯 Scenario-Based Generation: AI Evaluation Datasets with User Personas and Business Scenarios
123 views • 9 months ago
Knowledge
Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
35 views • 9 months ago
Knowledge
Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
47 views • 9 months ago
Technology
🫱🏾🫲🏼 Human Iteration on AI evals: Creating "Tasks" for Better Collaboration & Quality Control
69 views • 10 months ago
Knowledge