Eye on AI Weekly Research Watch cover art

Eye on AI Weekly Research Watch

Eye on AI Weekly Research Watch

By: Craig Spencer Smith
Listen for free

Weekly, digestible podcast explainers of significant research papers@ 2026 Eye on AI Politics & Government
Episodes
  • Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection

    Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection
    Jun 30 2026
    Financial fraud detection in transaction networks faces a fundamental challenge: fraudulent activity is rare, well-disguised, and often underrepresented in labeled data. Standard graph neural networks tend to smooth out the very irregularities that signal fraud. ADC-GNN tackles this with three complementary mechanisms: diffusion-guided feature augmentation that stabilizes node representations against noise, contrastive learning across perturbed views, and a spectral attention module that adaptively amplifies fraud-relevant frequency signals across multiple graph hops. Evaluated on public benchmarks and a real telecom transaction dataset, it consistently outperforms baselines under low-label conditions. Applications include credit card fraud detection, anti-money laundering systems, telecommunications billing abuse detection, and social network spam identification. Authors: Liming Liu, Chao Hu, Mingfei Lu, Yiwei Ge, Xingle Li, Heyuan Shi Paper: https://arxiv.org/abs/2606.28134v1
    Show More Show Less
    2 mins
  • Toward Robust In-Context Segmentation via Concept Guidance

    Toward Robust In-Context Segmentation via Concept Guidance
    Jun 30 2026
    In-context segmentation asks a model to identify target regions in new images using only a handful of labeled reference examples — no retraining required. Current approaches work by matching low-level visual features between references and queries, making them brittle when references vary in viewpoint, lighting, or appearance. CG-ICS instead extracts high-level semantic concepts from references using a multimodal language model, then uses these concepts alongside a spatial grounding route to guide a frozen SAM3 segmentation backbone. It achieves state-of-the-art accuracy and substantially reduced variance across diverse reference choices. Applications span medical image annotation, few-shot industrial inspection, and rapid domain adaptation in computer vision pipelines with limited labeled data. Authors: Zhigang Chen, Xiawu Zheng, Rongrong Ji Paper: https://arxiv.org/abs/2606.28149v1
    Show More Show Less
    2 mins
  • Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

    Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models
    Jun 30 2026
    Jailbreak attacks — prompts engineered to make safety-aligned LLMs produce harmful outputs — are a persistent concern, but exactly how they work mechanistically has remained murky. This paper provides evidence that successful attacks don't erase safety representations; they selectively suppress specific "Adversarially Compromised Heads" in early attention layers while leaving "Safety-Aligned Heads" in mid-layers largely intact. This residual safety signal is detectable without any additional training, and reading it yields competitive jailbreak detection performance with strong robustness. These findings have direct implications for LLM safety auditing, interpretability-based defenses, red-teaming methodologies, and the design of future architectures with more resilient safety mechanisms. Authors: Yanchen Yin, Dongqi Han, Linghui Li Paper: https://arxiv.org/abs/2606.28153v1
    Show More Show Less
    3 mins
adbl_web_anon_alc_button_suppression_t1
No reviews yet