{"id":451,"date":"2026-04-15T10:56:32","date_gmt":"2026-04-15T09:56:32","guid":{"rendered":"https:\/\/blogs.kent.ac.uk\/cyber-institute-news\/?p=451"},"modified":"2026-04-15T10:56:32","modified_gmt":"2026-04-15T09:56:32","slug":"icss-hosted-ai-ss-2026-1st-international-workshop-on-ai-safety-and-security","status":"publish","type":"post","link":"https:\/\/blogs.kent.ac.uk\/cyber-institute-news\/2026\/04\/15\/icss-hosted-ai-ss-2026-1st-international-workshop-on-ai-safety-and-security\/","title":{"rendered":"iCSS hosted AI-SS 2026 (1st International Workshop on AI Safety and Security)"},"content":{"rendered":"

On Tuesday 7 April 2026, iCSS hosted AI-SS 2026 (1st International Workshop on AI Safety and Security)<\/a>, as part of EDCC 2026 (21st European Dependable Computing Conference)<\/a>, in the Sibson Building on the main campus of the University of Kent in Canterbury, UK. Professor Shujun Li<\/a>, iCSS Director, was the Workshop\u2019s Co-Chair who managed the peer review process and took care of local arrangement matters. The Workshop\u2019s Chair is Professor Hongmei (Mary) He<\/a> from the University of Salford.<\/p>\n

The Workshop was technically sponsored by the following three organisations:<\/p>\n

    \n
  1. Institute of Cyber Security for Society (iCSS)<\/a> at the University of Kent, UK<\/li>\n
  2. Association of British Chinese Professors (ABCP)<\/a> through its Specialty Committee on AI and Cyber Security<\/a><\/li>\n
  3. AI-Cyber Special Interest Group (SIG)<\/a> of the CRANE NetworkPlus<\/a>, which aims to strengthen the UK\u2019s cyber security research ecosystem and is funded by the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI)<\/li>\n<\/ol>\n

    \"AI-SS<\/p>\n

    The Workshop also received technical support from multiple professional bodies. In particular, the IEEE UK and Ireland Section<\/a>, eight of its chapters and the Future Networks Local Group<\/a> helped disseminate the Workshop\u2019s call for papers. The eight IEEE UK and Ireland chapters include the Communications Chapter<\/a>, Computational Intelligence Chapter<\/a>, Computer Society Chapter<\/a>, Electronic Packaging and Reliability Joint Chapter<\/a>, Robotics and Automation Systems Chapter<\/a>, Signal Processing Chapter<\/a>, Society on Social Implications of Technology (SSIT) Chapter<\/a>, Sensors Council Chapter<\/a>, and Systems, Man, and Cybernetics Chapter.<\/a><\/p>\n

    The Workshop received 18 submissions from authors in seven countries, from which the following seven papers were accepted and presented at the Workshop in two technical sessions (one in the morning and the other in the afternoon).<\/p>\n

      \n
    1. HaiR \u2013 A Human-Centric AI Remediation Framework slides<\/em>
      \nOlayinka Adeboye, Rabab Al Zaidi, Aderemi Adenihun, Segun Akinseye, Lee Speakman and Muhammad Ateeq (University of Salford, UK)<\/li>\n
    2. An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios<\/em>
      \nCaglar Uysal, Baturay Birinci, Suha Mutluergil and Orcun Cetin (Sabanci Univeristy, T\u00fcrkiye)<\/li>\n
    3. Resilience to Disinformation Among Cyber Security and Information Warfare Professionals: Why Experts May Get it Wrong slides<\/em>
      \nAllison Wylde (University of Kent, UK), Fabio Petani (Universit\u00e9 Bourgogne Europe, Burgundy, France), Issa Issa (ESSCA, France) and Fortuna Cassoria (Universit\u00e9 Bourgogne Europe, Burgundy, France)<\/li>\n
    4. Leveraging Sparse Intelligence: Large Language Models Can Provide Actionable Priorities From Limited Cyber Threat Data<\/em>
      \nOsama Al Haddad (Macquarie University, Australia), Muhammad Ikram (Macquarie University, Australia), Muhammad Ejaz Ahmed (Data61, CSIRO, Australia) and Young Choon Lee (Macquarie University, Australia)<\/li>\n
    5. Agentic AI vs Non-Agentic AI: Motivation, Security Implications, and Research Foundations slides<\/em>
      \nShivangi Gupta, Budi Arief and Rog\u00e9rio de Lemos (University of Kent, UK)<\/li>\n
    6. Exploring Agentic AI in Anti-Forensics: Simulation of Evasion Tactics in Digital Investigations<\/em>
      \nAderemi Adenihun, Ifeoluwa Ojuolape Oria, Oseodion Ofeimun, Emmanuel Orji, Olayinka Adeboye Adeboye and Segun Akinseye (University of Salford, UK)<\/li>\n
    7. Agentic Knowledge Distillation: Autonomous Training of Small Language Models for SMS Threat Detection slides<\/em>
      \nAdel ElZemity, Joshua Sylvester, Budi Arief and Rog\u00e9rio de Lemos (University of Kent, UK)<\/li>\n<\/ol>\n

      In the morning, the technical programme of the one-day Workshop also included a keynote talk on “The Uneasy Marriage of AI and Dependability”, given by Professor Aad van Moorsel<\/a>, Chair in Decentralised Systems & Head of School, School of Computer Science, University of Birmingham.<\/p>\n

      \"AI-SS<\/p>\n

      The afternoon session of the Workshop started with a panel discussion on \u201cTowards Dependable and Secure AI for Critical Systems\u201d, facilitated by the Workshop Chair Professor Hongmei (Mary) He and participated in by the following four panellists:<\/p>\n