Crafting evasive phishing URLs: exploiting tokenizer vulnerabilities in transformer-based detection systems

Adversarial-resilient lightweight phishing url detection: Evaluating lexical & metadata features under evasion techniques

The Adversarial-Resilient Lightweight Random Forest (AR-LRF) model is proposed, combining controlled ensemble complexity with simulated adversarial perturbations applied during training to mitigate adversarial vulnerabilities.

Adversarial Robustness in Smishing Detection: A Comparative Analysis of Adversarial Fragility in Classical vs. Transformer-Based Detection Systems

It is demonstrated that clean-text performance is not a reliable predictor of adversarial robustness, and the results underscore the necessity for architecture-specific defences and frame smishing detection as an adversarial cybersecurity challenge rather than a static classification task.

Adversarial Prompts for Acceptance Collapse in Speculative Decoding

ADSD is introduced, which is the first prompt-suffix attack that collapses verifier acceptance by pushing draft probability mass toward tokens the target is unlikely to accept, and successfully generates highly effective adversarial suffixes.

Phishing GAT: Adversarial-Hardened Phishing Email Detection via Semantic-Structural Fusion and Graph Attention Networks

PhishingGAT, a detector that fuses word-level semantic features with structural ones and is hardened against adversarial perturbation, is presented, a detector that fuses word-level semantic features with structural ones and is hardened against adversarial perturbation.

: Can We Trust GenAI Recommendations? Unpacking Adversarial Vulnerabilities in LLM/VLM Ranking Systems

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments

AlIBI is presented, an automated adaptive black-box attack framework that generates and iteratively refines adversarial comments using detector reasoning and feedback and is motivated to motivate security-aware designs that carefully calibrate trust between natural-language context and program evidence.