Embracing AI to Build Resilience Against AI Attacks

Virtual: https://events.vtools.ieee.org/m/482836

Join IEEE Women in Engineering (WIE) Chicago and Region 4 for an inspiring WIE Day 2025 event focused on cybersecurity. Our featured speaker, Aparna Achanta, Principal Security Architect at IBM Consulting, will present: "Embracing AI to Build Resilience Against AI Attacks" Aparna has extensive experience driving mission-critical cybersecurity initiatives, particularly in federal agencies. She successfully implemented cybersecurity frameworks like Zero Trust and Security by Design for U.S. Federal Clients thereby strengthening the security posture and enhancing data protection and security standards across cloud applications. She specializes in securing Emerging technologies in federal agencies, including low-code, No-Code applications, and Generative AI applications. She is a member of the Forbes Technology Council and a passionate advocate for women in tech. She is a founding member and speaker at the WomenTech Network and also serves as an executive board member at Women in Cybersecurity (WiCyS) Austin Chapter. The sheer complexity and volume of cyber threats are scaling cybersecurity teams to breaking point. The unprecedented pace at which AI is evolving means there is little time for proactive measures; teams must adopt an immediate crisis management approach. The sophistication of such threats is changing the game on how security is done. Traditional models based on determinism—where something is identified as a threat or not—give way to probabilistic approaches, which focus on interpreting ambiguous signals and investigating anomalies that may indicate potential threats. Arpana's talk focuses on how AI amplifies threat detection through automation, taking responses to the next level. AI can generate high-quality probabilistic insights, allowing teams to decide whether intricate patterns that seem harmful are malicious or benign anomalies- a capability unique to AI since conventional algorithms within the security framework cannot handle such subtle analysis. This event is a great opportunity for anyone interested in cybersecurity, AI, and the important role women play in advancing innovation. Don’t miss the chance to learn from an expert and connect with a community that supports growth and resilience in tech. Virtual: https://events.vtools.ieee.org/m/482836

IEEE Annual Picnic

1021 Mustang Drive, Bismarck, North Dakota, United States, 58503

Please join us for the Missouri Slope IEEE annual Picnic at the New Generation Park Far West Rotary Community Center on June 24th from 5:00-7:30 PM. IEEE will be providing dinner and dessert, as well as non-alcoholic and alcoholic beverages. Please RSVP and tell the number of people attending by June 17th for an accurate headcount for the catering and drinks. 1021 Mustang Drive, Bismarck, North Dakota, United States, 58503

MOVE USA Jun 2025 Tech Talk – Convoy of Hope

Virtual: https://events.vtools.ieee.org/m/463714

Convoy of Hope is a faith-based humanitarian organization dedicated to transforming lives in the U.S. and around the world. With a focus on ending generational poverty, Convoy runs impactful programs including children’s feeding initiatives, women’s empowerment efforts, and sustainable agriculture development. Beyond these core programs, Convoy of Hope is a critical first responder when disaster strikes. With a specialized fleet of vehicles and a trained response team, they deliver essential relief supplies to communities hit by natural and humanitarian crises. In 2024 alone, Convoy responded to 99 disasters both domestically and internationally. What sets Convoy’s Disaster Response team apart is their innovative model for serving survivors—something we’ll explore in more detail during the MOVE USA Tech Talk. Co-sponsored by: IEEE-USA MOVE Program Speaker(s): Ethan Forhetz Virtual: https://events.vtools.ieee.org/m/463714

Generic LLMs in Cybersecurity

Virtual: https://events.vtools.ieee.org/m/489327

Generic Large Language Models (GLLMs) are continually being released with increased size and capabilities, enhancing the capabilities of these tools as universal problem solvers. While the reliability of GLLMs' responses is questionable in many situations, these models are often augmented or retrofitted with external resources for various applications, including cybersecurity. The talk will discuss major security concerns of these pre-trained models: first, GLLMs are prone to adversarial manipulation, such as model poisoning, reverse engineering, and side-channel cyberattacks. Second, the security issues related to LLM-generated codes using open-source libraries/codelets for software development can involve software supply chain attacks. These may result in information disclosure, access to restricted resources, privilege escalation, and complete system takeover. This talk will also cover the benefits and risks of using GLLMs in cybersecurity, particularly in malware detection, log analysis, intrusion detection, etc. I will highlight the need for diverse AI approaches (non-LLM-based smaller models) trained with application-specific curated data, fine-tuned for well-tested security functionalities in identifying and mitigating emerging cyber threats, including zero-day attacks. Note: - You will require a Zoom account (free to obtain) to join the meeting. This requirement is to avoid Zoom bombing. Please sign in using the email address tied to your Zoom account, not necessarily the one you used to register for the event. Register here: https://sjsu.zoom.us/meeting/register/2XuaGc9ISoCWOu1dt6ANog - By registering for this event, you agree that IEEE and the organizers are not liable to you for any loss, damage, injury, or any incidental, indirect, special, consequential, or economic loss or damage (including loss of opportunity, exemplary or punitive damages). The event will be recorded and will be made available for public viewing. Co-sponsored by: Vishnu S. Pendyala, SJSU Speaker(s): Dr. Vishnu S. Pendyala, Prof. Dipankar Dasgupta, IEEE Fellow, NAI Fellow, AIIA Fellow Virtual: https://events.vtools.ieee.org/m/489327