Track upcoming talks, workshops, conferences, and related event references across AI security, governance, and adjacent engineering work.
Search by event or location, narrow by topic and format, or focus on the next 90 days.
72 upcoming events
The ninth AAAI/ACM Conference on AI, Ethics, and Society convenes technical, legal, philosophical, and social-science research in Malmö. The 2026 program examines the governance and societal consequences of AI systems as they move from experimental tools into entrenched infrastructure.
AI Security Summit San Francisco is a one-day, two-track event for security leaders and practitioners covering AI governance, vendor risk, prompt injection, jailbreak defense, red teaming, and incident response.
OpenAI DevDay Exchange in Bengaluru offers technical sessions, project discussion, and hands-on guidance with OpenAI engineering teams. The organizer describes real application projects and coding-agent workflows. Attendance requires an application; the event begins at 2 p.m. local time, with venue details and the full program supplied after approval.
OpenAI DevDay Exchange in Tokyo offers technical sessions, project discussion, and hands-on guidance with OpenAI engineering teams. The organizer describes real application projects and coding-agent workflows. Attendance requires an application; the event begins at 2 p.m. local time, with venue details and the full program supplied after approval.
Cloud Security Alliance holds this free virtual summit on October 21–22. Its current overview focuses on controlling autonomous-agent actions through AARM and previews STAR for AI Level 2 and approaches to agent assurance. The overview establishes the topic and dates; it does not provide a finalized technical session schedule.
The Conference on Applied Machine Learning in Information Security brings researchers and practitioners from industry, academia, and government to Arlington to discuss machine learning and cybersecurity.
Zenity’s AI Agent Security Summit takes place October 21 at Pier Sixty in New York City. The organizer’s overview discusses agent autonomy, connector and MCP exposure, employee permissions, and shared responsibility for enterprise agents. The inspected event page confirms the venue and date, but its session agenda is not yet available.
OpenAI DevDay Exchange in Seoul offers technical sessions, project discussion, and hands-on guidance with OpenAI engineering teams. The organizer describes real application projects and coding-agent workflows. Attendance requires an application; the event begins at 2 p.m. local time, with venue details and the full program supplied after approval.
AGNTCon + MCPCon North America 2026 brings agent and MCP builders to San Jose to cover production architectures, protocols, infrastructure, security, governance, observability, and interoperability.
ISC2 Security Congress 2026 takes place in Denver and online with professional sessions on AI security and governance, GenAI risk, GRC, and scenario-based AI Incident Rooms.
AltSecCON runs October 24–27 at Hilton EGL in Bengaluru: training occupies October 24–26 and the conference follows on October 27. The published course catalog includes AI red teaming across Microsoft 365 Copilot, Copilot Studio, and Azure AI environments, with labs examining agents, connectors, permissions, and prompt injection.
OpenAI DevDay Exchange in Berlin offers technical sessions, project discussion, and hands-on guidance with OpenAI engineering teams. The organizer describes real application projects and coding-agent workflows. Attendance requires an application; the event begins at 2 p.m. local time, with venue details and the full program supplied after approval.
Black Hat India runs October 27–30 in Bengaluru. Technical training takes place October 27–28, followed by research briefings and open-source tool demonstrations on October 29–30. The event covers security more broadly than AI; choose individual sessions or courses for their tested methods and relevance to the systems you operate.
[un]prompted II is a practitioner-led AI-security conference in San Francisco organized around building, breaking, operating, governing, and training AI systems. Its review criteria favor production architecture, metrics, failures, demonstrations, code, and prompts over pre-deployment speculation.
OpenAI DevDay Exchange in Paris offers technical sessions, project discussion, and hands-on guidance with OpenAI engineering teams. The organizer describes real application projects and coding-agent workflows. Attendance requires an application; the event begins at 2 p.m. local time, with venue details and the full program supplied after approval.
GAISS 2026 is an IEEE conference at the University of Texas at Austin focused on generative AI for secure systems, including red teaming, blue-team automation, governance, and agentic secure AI.
OWASP Global AppSec USA runs November 2–6 in San Francisco. Training takes place November 2–4, followed by the main conference November 5–6. It brings application-security practitioners, developers, and researchers together; use the session and course details to identify material relevant to AI-enabled applications and secure development.
The SANS AI Cybersecurity Summit brings practitioners to Arlington and a virtual audience together for technical sessions, workshops, and case studies on AI-powered attacks, defensive uses of AI, and secure adoption.
OpenAI DevDay Exchange in London offers technical sessions, project discussion, and hands-on guidance with OpenAI engineering teams. The organizer describes real application projects and coding-agent workflows. Attendance requires an application; the event begins at 2 p.m. local time, with venue details and the full program supplied after approval.
SecureWorld Seattle 2026 is a two-day professional cybersecurity conference in Bellevue with sessions on prompt injection, model poisoning, AI governance, NIST AI RMF implementation, shadow AI, and secure enterprise deployment.
OpenAI DevDay Exchange in São Paulo offers technical sessions, project discussion, and hands-on guidance with OpenAI engineering teams. The organizer describes real application projects and coding-agent workflows. Attendance requires an application; the event begins at 2 p.m. local time, with venue details and the full program supplied after approval.
Agentics Day: MCP + Agents takes place November 9 in Salt Lake City alongside KubeCon + CloudNativeCon North America. Its scope includes MCP implementations, production agent infrastructure, and security, trust, and reliability. Access is through the parent conference’s All-Access in-person registration option.
OpenAI DevDay Exchange in Mexico City offers technical sessions, project discussion, and hands-on guidance with OpenAI engineering teams. The organizer describes real application projects and coding-agent workflows. Attendance requires an application; the event begins at 2 p.m. local time, with venue details and the full program supplied after approval.
TrustAudio is a one-day AACL-IJCNLP workshop in Zhuhai focused on security, safety, and privacy across the speech and audio AI lifecycle, including adversarial audio, real-world attacks, deepfake misuse, backdoors, model provenance, and system safeguards.
SecureAI.se runs November 10–12 at Nalen in Stockholm. Two days of training precede the November 12 conference. The published offering includes pentesting LLM applications and agents; conference themes cover threat modeling, secure ML pipelines, infrastructure, and governance. Announced talks also examine AI-generated vulnerability reports and software supply-chain risks.
The hybrid AI Engineer Code Summit takes place November 10–12 at Hilton Union Square in San Francisco, with a livestream also announced. Workshops are November 10; the main conference is November 11–12. The announced focus is coding agents, development workflows, code review, evaluations, and supporting infrastructure. Speakers and a detailed session program remain forthcoming.
The 19th ACM Workshop on Artificial Intelligence and Security is listed for November 15 in ACM CCS registration, alongside related workshops in The Hague. It covers adversarial ML, model privacy, AI misuse, foundation-model red teaming, dangerous-capability evaluation, deceptive alignment, multi-agent risk, and autonomous-agent containment.
The 33rd ACM Conference on Computer and Communications Security brings peer-reviewed security and privacy research to the World Forum in The Hague, including a large workshop program on November 15 and 19.
This ACM CCS workshop meets November 15 at the World Forum in The Hague. It studies security, privacy, and safety of agents that use tools, retain memory, execute code, or coordinate with other agents. Its scope includes memory poisoning, permission abuse, prompt injection, data leakage, and system-level evaluation beyond the underlying model.
The AI Governance Conference 2026 is co-located with DGIQ East in Providence and focuses on enterprise AI governance, risk, compliance, data quality, and operational leadership.
This IAPP event in Brussels covers privacy, AI governance, and cybersecurity law. Training runs November 16–17, workshops take place November 17, and the main conference runs November 18–19. Review the relevant pass and session program when planning attendance; the full calendar range includes the pre-conference education days.
Cloud Security Alliance lists a free in-person Verifiable Agent Summit in San Francisco on November 16. Its announced subject is verification of AI agent actions, authority, and trust. The current organizer calendar confirms the date and city, but does not yet supply a detailed session agenda or a venue address.
Cloud Security Alliance's free two-day virtual AI Security Summit examines how Zero Trust principles apply to AI systems, agents, cloud infrastructure, identities, data, and runtime controls.
MCP Dev Summit Nairobi 2026 brings developers and operators together for two days on Model Context Protocol implementation, production infrastructure, interoperability, security, and governance.
TrustAICyberSec is a November 19 ACM CCS workshop at the World Forum in The Hague. Its research scope connects trusted computing and attestation with AI-assisted attack detection, incident response, and security of embedded and networked systems. The workshop website describes the research scope; CCS supplies the specific workshop date.
ESSAI takes place November 19 in Rennes, France, during European Cyber Week. Organized by Inria and AMIAD, the research symposium has two themes: agentic AI for offensive and defensive cybersecurity, and security of AI systems themselves. Attendance is free, with registration required.
This forum takes place November 22 at the Tel Aviv Museum of Art, with talks and workshops on frontier-model security. Announced discussion topics include controlling untrusted AI, internal deployment security, backdoors, and hardware verification. Attendance is application-based, and the public overview describes planned topics rather than a final session schedule.
This half-day summit meets November 25 at Doltone House Hyde Park in Sydney. Published sessions examine threat modeling before deployment, penetration testing of real AI applications, and a security knowledge graph compared with document retrieval under the same evaluation conditions. Other sessions discuss operational AI-security programs and agent identity.
Black Hat Middle East & Africa 2026 brings security practitioners and researchers to Malham, Riyadh for three days of technical content, competitions, tools, and industry programming.
This IAPP event in Sydney covers privacy, AI governance, and cybersecurity law. Training runs December 1–2, and the main conference runs December 3–4. Review the relevant pass and session program when planning attendance; the full calendar range includes the pre-conference education days.
NeurIPS 2026 runs in Sydney December 6–12, with Atlanta and Paris satellite programs December 9–13. Sydney’s main conference is December 8–10 and its workshops are December 11–12; satellite workshops fall December 12–13. Several Sydney workshops examine agent security, trustworthy evaluation, and supervision of autonomous systems.
Black Hat Europe 2026 brings security researchers and practitioners to London for four days of technical training, review-board-selected Briefings, Arsenal tool demonstrations, and a dedicated AI Security Summit.
ACSAC runs December 7–11 in Los Angeles, with a 2026 focus on security and privacy of agentic systems. Its AI-related workshops include offensive and defensive agents, biotechnology AI safety, and AI for threat intelligence on December 7, followed by resilient and trustworthy machine learning on December 8.
AIDC is a December 7 ACSAC workshop in Los Angeles on agentic AI for offensive and defensive cyber operations. Its research scope includes interactions between attacking and defending agents, deception, input manipulation, poisoning, and failures in operational environments. The emphasis is on evaluating complete cyber workflows rather than isolated model capabilities.
WAITI is a December 7 ACSAC workshop in Los Angeles on applying AI to cyber threat intelligence. Its scope includes extracting and organizing threat information with NLP and language models, analyzing malware and network behavior, and intelligence for IoT environments. It brings together research on AI methods and operational threat-intelligence needs.
BioAISS meets December 7 alongside ACSAC in Los Angeles. The workshop studies security and safety of AI-enabled biotechnology and healthcare systems, including sensitive-data protection, model robustness, secure pipelines, threat modeling, and governance. Its call for papers emphasizes evaluation methods, practical systems, and deployment experience across technical and policy disciplines.
ARTMAN takes place December 8 alongside ACSAC in Los Angeles. The workshop examines resilient and trustworthy machine-learning systems through testing, simulation, verification, and validation. Its scope includes adversarial threats, accidental failures, transparency, and the relationship between ML components and the larger systems in which they operate.
This NeurIPS workshop takes place December 11 in Sydney. It examines safety and security of agents that act through tools, maintain state, and interact with changing environments. The program addresses adversarial threats and failures that emerge when models become operational systems, connecting foundational research with deployment experience.
This NeurIPS workshop meets December 11 in Sydney. It studies systems in which agents design, supervise, or improve other agents, including benchmarks, optimization, and oversight. Security-relevant questions include propagation of misaligned goals, verifiable stopping controls, and the ability of people to supervise increasingly layered agent systems.
This NeurIPS workshop meets December 12 in Sydney and focuses on reliable agent development through verification. Topics include verifiers that resist reward hacking, evaluations grounded in realistic environments, and the cost, latency, and calibration of checking agent behavior. The program examines both verification methods and how they shape agent training.
This NeurIPS workshop takes place December 12 in Sydney and examines robustness, causality, and risk in AI evaluation. Its scope includes data contamination, repeated benchmark use, fragile protocols, and the gap between benchmark results and deployment decisions. The program asks what kinds of evidence support reliable conclusions about AI systems.
The 41st AAAI Conference on Artificial Intelligence takes place in Montréal with technical papers, workshops, tutorials, competitions, and programs spanning AI research and practice.
Black Hat Asia 2027 returns to Singapore for four days of security training, research briefings, tool demonstrations, and industry programming.
Agentics Day: MCP + Agents takes place March 15 in Barcelona alongside KubeCon + CloudNativeCon Europe. The call for proposals covers MCP clients and servers, production deployment, debugging, observability, and security, trust, and reliability. These are announced submission topics, not a finalized session program. Access is through the parent conference’s All-Access in-person pass.
This IAPP event in Washington, D.C. covers privacy, AI governance, and cybersecurity law. Training runs March 21–22, workshops take place March 22, and the main conference runs March 23–24. Review the relevant pass and session program when planning attendance; the full calendar range includes the pre-conference education days.
NDSS Symposium 2027 brings a leading peer-reviewed network and distributed-systems security conference to Seoul, with a practical focus on real systems, design, implementation, and deployable security technologies.
This IAPP event in London covers privacy, AI governance, and cybersecurity law. Training runs April 5–6, workshops take place April 6, and the main conference runs April 7–8. Review the relevant pass and session program when planning attendance; the full calendar range includes the pre-conference education days.
RSAC 2027 returns to San Francisco for four days of cybersecurity research, professional education, product strategy, governance, and practitioner networking.
ICLR 2027 runs April 26-30 in California, with the main conference April 26-28 followed by workshops April 29-30. The detailed program remains unannounced, so this entry does not assume a dedicated security or safety track.
AGNTCon + MCPCon’s 2027 event in San Francisco is announced for the dates shown. The community focuses on building agents and Model Context Protocol integrations, but the current event page is a save-the-date notice. A detailed program, speakers, and specific security sessions have not yet been published.
IEEE SaTML takes place May 3–6 in Reykjavik, Iceland. Workshops on May 3 precede the main conference on May 4–6. The research scope includes attacks and defenses for machine learning, privacy, system verification, and security in deployed ML. Announced workshops cover reproducible security research, trustworthy tabular models, collaborative learning, and human-centered ML security.
The 48th IEEE Symposium on Security and Privacy takes place May 17–19 at Le Centre Sheraton in Montréal, with associated workshops on May 20. It publishes peer-reviewed computer-security and privacy research. The full four-day calendar range includes both the main symposium and workshops; specific 2027 AI-security sessions remain to be announced.
This IAPP event in Toronto covers privacy, AI governance, and cybersecurity law. Training runs May 25–26, workshops take place May 26, and the main conference runs May 27–28. Review the relevant pass and session program when planning attendance; the full calendar range includes the pre-conference education days.
ACM FAccT 2027 convenes interdisciplinary research on responsible, safe, ethical, and trustworthy computing. Its official scope includes AI red teaming and adversarial testing, assurance and deployment policy, audits, model and system evaluation, governance, sociotechnical safety, and threat models and mitigations.
OWASP Global AppSec EU 2027 brings application-security practitioners, developers, and researchers to Vienna for training and conference sessions on current software-security risks and defenses.
PETS 2027 brings privacy researchers and practitioners to Delft for six days of peer-reviewed research, workshops, and discussion on privacy-enhancing technologies and deployed systems.
Black Hat USA 2027 returns to Mandalay Bay in Las Vegas for six days of security training, research briefings, tool demonstrations, and industry programming. The detailed 2027 agenda has not yet been published.
DEF CON 35 is scheduled for August 5-8, 2027 at the Las Vegas Convention Center, bringing together security researchers, practitioners, villages, contests, and community-led technical programs.
The 36th USENIX Security Symposium brings security and privacy researchers and practitioners to Denver to present advances in the security of computer systems and networks.
IAPP Privacy. Security. Risk. + AI Governance Global 2027 will convene privacy, cybersecurity law, technology, and AI governance professionals in Vancouver.
AGNTCon + MCPCon’s 2027 event in London is announced for the dates shown. The community focuses on building agents and Model Context Protocol integrations, but the current event page is a save-the-date notice. A detailed program, speakers, and specific security sessions have not yet been published.
OWASP Global AppSec USA 2027 brings application security practitioners, developers, and researchers to Atlanta for training and conference sessions on current software-security risks and defenses.
Archived events, recordings, and related notes that still provide useful context.
The AI Agent Security Summit in London is a one-day practitioner event focused on securing enterprise agents, identities, tools, data access, governance, and runtime activity.
SecTor's one-day AI x Cloud Security Summit in Toronto covers AI-driven attacks and defenses, securing AI workloads, cloud-native security architecture, governance and risk, and the changing security-operations model.
IAPP Privacy. Security. Risk. + AI Governance Global 2026 brings privacy, cybersecurity law, technology, and AI governance professionals together in Seattle.
MCP Dev Summit Toronto 2026 brings developers and operators together for two days on Model Context Protocol implementation, production infrastructure, interoperability, security, and governance.
OpenAI DevDay 2026 is scheduled for September 29 in San Francisco and is OpenAI’s primary developer event for platform updates.
OASec is a one-day Singapore forum dedicated to AI safety and security, organized across enterprise, governance, offense, and defense tracks. Its scope includes production architectures, policy and compliance, red teaming, jailbreaks, prompt injection, tool abuse, guardrails, incident response, and secure-by-design practices for foundation models and agentic systems.
AMLUCS is a two-day, not-for-profit practitioner conference in London dedicated to applied AI and machine learning in cybersecurity. Its twin-track scope includes AI-system threats and mitigations, offensive and defensive AI, multi-agent design, governance and standards, and a preceding production AI red-team training course.
[un]prompted.au is a two-day practitioner-led AI-security conference at ILUMINA in Sydney focused on building, breaking, operating, and governing real AI systems.