Loading story…
Researchers from Microsoft and partner organizations have identified a critical vulnerability in current biosecurity screening systems used by DNA synthesis companies. These systems are designed to prevent the synthesis of DNA sequences that could be used to create dangerous toxins or pathogens by scanning orders for known threat sequences. However, advances in AI-assisted protein engineering have enabled the design of novel proteins, including modified versions of known toxins such as ricin, that can evade these traditional screening methods. In confidential studies, AI protein design (AIPD) tools were shown to generate protein sequences that, while functionally similar to known toxins, were sufficiently different at the DNA level to bypass existing biosecurity checks. This discovery has been likened to a 'biological zero-day,' representing an unrecognized and unmitigated security gap in the biosecurity infrastructure. The research team conducted a two-year project, including a 10-month confidential collaboration with stakeholders across sectors, to develop and test new 'red-teaming' methods for identifying and addressing these vulnerabilities. Their work culminated in the development of practical 'patches'—enhanced screening protocols and tools—that have now been adopted globally to make DNA synthesis screening more resilient against AI-generated threats. The findings highlight the dual-use nature of AI in biology, where the same technologies that promise breakthroughs in medicine and materials science can also be misused to create novel biological threats. The researchers' approach drew on methodologies from the cybersecurity community, adapting them to the unique challenges of biosecurity. The study, published in Science, underscores the urgent need for ongoing vigilance and adaptation of biosecurity measures as AI capabilities continue to evolve. The incident demonstrates that as AI tools become more sophisticated, traditional security controls may become obsolete unless they are continuously updated. The research also emphasizes the importance of cross-sector collaboration in identifying and mitigating emerging threats. The global adoption of the new screening measures represents a significant step forward in biosecurity, but the researchers caution that the threat landscape will continue to change. The case serves as a warning that AI-driven innovation in biology must be matched by equally innovative security practices. The work also raises broader questions about the governance and oversight of dual-use technologies in the life sciences. The researchers advocate for ongoing research, transparency, and international cooperation to ensure that the benefits of AI in biology are realized safely. The incident has prompted renewed discussion among policymakers, industry, and the scientific community about the adequacy of current biosecurity frameworks. The study's impact is already being felt, with DNA synthesis companies worldwide updating their protocols to address the newly identified risks. The episode illustrates the growing intersection of cybersecurity and biosecurity in the age of AI.
Track how attackers are adapting to this technology.
5 events from the most recent confirmed update back to the earliest known activity.
Media coverage and public commentary in early October 2025 drew broader attention to the risk that AI-designed proteins could bypass threat-screening tools. The reporting framed the issue as a potential new biosecurity vulnerability created by advances in generative biology tools.
By the time of public disclosure, the researchers and IBBIS had established a tiered-access framework to control access to sensitive methods and data, using access requests, information tiers, and usage agreements. Science leadership formally endorsed the approach, and Microsoft provided an endowment to help sustain the program.
On October 2, 2025, the paper "Strengthening nucleic acid biosecurity screening against generative protein design tools" was published in Science. It reported computer-based studies showing AI-assisted protein design could generate modified proteins of concern, such as ricin variants, that might evade DNA synthesis screening systems.
Over a 10-month collaboration, researchers and cross-sector partners created biosecurity red-teaming methods and screening updates to address gaps exposed by AI-designed proteins. The resulting patches were adopted globally before the findings were publicly disclosed.
Researchers began a confidential, two-year effort in late 2023 to study whether AI-assisted protein design could create harmful proteins that evade existing biosecurity screening systems. The work was kept nonpublic initially to reduce information-hazard risks while mitigations were developed.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
2 references tracked. Mallory keeps watching after this page renders.
Map indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Security researchers and industry experts are raising alarms about the growing use of artificial intelligence (AI) in both offensive and defensive cybersecurity operations. Attackers are leveraging AI to bypass advanced security controls, as demonstrated by a researcher who used AI to defeat an "AI-powered" web application firewall, and by the emergence of new malware that exploits AI model files and browser vulnerabilities to evade detection and exfiltrate credentials. Meanwhile, defenders are grappling with the proliferation of unsanctioned AI tools in the workplace, the challenge of auditing AI decision-making, and the surge in AI-powered bug hunting, which has led to a dramatic increase in vulnerability discoveries and bug bounty payouts. The risks are compounded by the lack of clear AI usage policies, the potential for data leaks through generative AI tools, and the difficulty in monitoring or controlling how sensitive information is processed and stored by these systems. Industry reports highlight that a significant portion of employees use unauthorized AI applications, often exposing sensitive data without IT oversight, and that prompt injection and model manipulation are now common vulnerability types. The security community is also debating the extent to which ransomware and other attacks are truly "AI-driven," with some reports criticized for overstating the role of AI in current threat activity. As organizations rush to adopt AI for efficiency and innovation, experts urge the implementation of robust governance, continuous monitoring, and red-teaming to anticipate and mitigate the evolving risks posed by both sanctioned and shadow AI systems. The rapid evolution of AI in cybersecurity is forcing a reevaluation of traditional defense models, emphasizing the need for transparency, operational oversight, and adaptive security strategies.
Jun 29, 2026
A demonstration of an academic AI-powered ransomware prototype caused significant alarm, highlighting the growing risk that experimental AI malware could inadvertently spark real-world crises. The incident underscored how the boundary between controlled lab environments and live cyber threats is increasingly blurred, raising concerns among security professionals about the potential for accidental or intentional misuse of AI-driven attack tools. Simultaneously, security experts have warned that attackers are leveraging AI to automate ransomware campaigns, craft sophisticated phishing attacks, and deploy deepfake technologies for espionage, such as infiltrating job interviews. These developments illustrate the expanding threat landscape posed by generative AI, emphasizing the urgent need for robust risk management and security controls to address both experimental and operational AI-enabled cyber threats.
Jun 29, 2026
The rapid advancement of artificial intelligence is fundamentally transforming both the threat landscape and defensive strategies in cybersecurity. Attackers are leveraging AI to create sophisticated deepfakes, automate penetration testing, and develop new forms of malware that can bypass traditional security controls. Notably, a real-world incident involving the engineering firm Arup saw deepfake impersonation used to steal $25 million, highlighting the tangible risks posed by AI-powered social engineering. Security professionals are responding by developing autonomous threat-hunting tools and digital twins to counteract adversarial AI bots, but the arms race is escalating, with attackers often gaining the upper hand due to the speed and scale enabled by AI. Researchers and practitioners emphasize the need for smarter, AI-aware authentication and proactive defense mechanisms to keep pace with evolving threats. At a strategic level, experts warn that the accelerating pace of AI innovation is outstripping the ability of national security and defense systems to adapt, potentially leading to strategic surprises and undermining long-term planning. AI's ability to rapidly test and deploy new attack techniques, such as autonomous penetration testing bots that have discovered critical vulnerabilities in widely used products, is shifting the economics and dynamics of cybersecurity. Organizations are urged to rethink their security postures, invest in continuous threat hunting, and prepare for a future where AI-driven attacks and defenses operate at a velocity and complexity beyond human tracking. The consensus is clear: the AI arms race in cybersecurity is intensifying, and both attackers and defenders must evolve rapidly to survive.
Jun 29, 2026