Cybersecurity

Smarter Email Dataset to Tackle Phishing and Spam

Kari Jaaskelainen

27 Nov 2025 — 1 min read

Smarter email defenses, grounded in real messages

Phishing and spam are evolving fast—often with help from AI. This study releases a large, carefully labeled email dataset spanning phishing, spam, and legitimate messages, with a key twist: it marks whether each message was written by a human or an LLM.

Every email also includes rich annotations: emotional tactics (like urgency, fear, or authority) and the attacker’s goal (link-clicks, credential theft, or financial fraud). The authors benchmark multiple LLMs to spot these cues, select the most reliable model to scale up labeling, and then stress-test robustness by rephrasing emails with several LLMs while preserving intent.

Results: today’s top models are strong at catching phishing, but still struggle to tell spam from genuine emails—an important gap for safer inboxes.

The dataset, code, and templates are openly available to accelerate research and deploy better defenses. Learn more: https://arxiv.org/abs/2511.21448v1

Paper: https://arxiv.org/abs/2511.21448v1

Register: https://www.AiFeta.com

cybersecurity AI LLM EmailSecurity Phishing SpamDetection Dataset OpenScience

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Smarter email defenses, grounded in real messages

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A