Category
1,407 papers
Retrieval-augmented Web applications increasingly employ multi-agent debate (MAD) to aggregate conflicting, noisy, and heterogeneous information, yet deliberation is fundamentally a social process susceptible to interpersonal dynamics. When retrieved Web sources contain latent hazards alongside safe factual content, so...
Most malware detection research focuses on identifying whether a file is malicious before it executes. Far less attention goes to what happens after infection. This paper presents an empirical analysis of post-infection malware behavior across 37 families, grounded in dynamic sandbox execution using CAPEv2. Behavioral...
Third-party Agent Skills extend what an autonomous agent can do, but a malicious Skill can hide data exposure or output manipulation inside a legitimate workflow. Neither reading a Skill's description nor granting it tool permissions tells whether its execution meets the user's security requirements. We introduce Runti...
Restricting what a model can say is often mistaken for restricting an attacker's influence over its decision. An attacker can add text to the evidence and steer the model toward a wrong answer that still belongs to the allowed set. We evaluate seven decision models spanning hosted APIs, open-weight models and an encode...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large Language Models (LLMs) have shown promise for empowering search agents to tackle complex information-seeking tasks. However, since acquiring external information necessitates web search, these agents are highly susceptible to various adversarial attacks (e.g., malicious information injection or stealthy context m...
Third-party LoRA adapters introduce serious backdoor risks: malicious adapters can maintain normal task performance while embedding hidden, trigger-activated behaviors, making them difficult to detect through standard utility evaluations. Existing removal-based defenses typically sanitize backdoored models by updating,...
Keystroke dynamics constitute a cost-effective behavioral biometric, but their timing features degrade under environmental and hardware variation. We replace these features with 19 dimensions of finger pressure and hand kinematics, sampled around each keystroke by a custom data glove - ten piezoresistive pressure senso...
It is demonstrated that MCP tool-call traces can act as effective behavioral side channels for user profiling, motivating the development of privacy-aware mechanisms for agent-tool interactions.
Aligned RAG Evaluation is introduced, a matched-query protocol that jointly examines clean and poisoned responses, with and without defense, and exposes critical blind spots in ASR-based evaluation and motivates a more comprehensive assessment of RAG poisoning defenses.
This work introduces Expected Harm, a metric that weights the severity of a jailbreak by its execution likelihood, modeled as a function of execution cost, and demonstrates that this miscalibration creates a vulnerability that increases the attack success rate of existing jailbreaks by up to $2\times.
Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates, is introduced and shows that prompt injection robustness can be achieved and improved through targeted attention interventions.
Centralized exchanges (CEXs) are key gateways between traditional finance and digital asset markets, yet identifying their blockchain addresses remains challenging. Existing approaches often rely on opaque attribution labels or treat exchanges as secondary classification targets, leaving generalization to unseen exchan...
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
GPT-Lab
· gpt-lab.eu
Oct 30, 2026
Critical flaws, compromised release channels and agentic AI threats landed within days of each other in mid-October 2026. Why “Black October” may say more about how well we now find weaknesses than about the attacks themselves. The post Black October? The Week AI Changed the Cybersecurity Conversation appeared first on GPT-Lab.
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
Gemini 3.8 Flash and 3.8 Flash Cyber deliver next-generation intelligence for agentic workflows and cybersecurity.
Google introduces Gemini 3.5 Flash Cyber, a lightweight cybersecurity model to find and patch vulnerabilities.
Students from the MIT Cybersecurity Clinic help local governments and other vulnerable organizations defend against digital threats.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
