Security in AI

Trending
6papers
4.2viability
+400%30d

Papers

1–6 of 6
Research Paper·Mar 12, 2026

BackdoorIDS: Zero-shot Backdoor Detection for Pretrained Vision Encoder

Self-supervised and multimodal vision encoders learn strong visual representations that are widely adopted in downstream vision tasks and large vision-language models (LVLMs). However, downstream user...

8.0 viability
Research Paper·Jan 16, 2026

LoRA as Oracle

Backdoored and privacy-leaking deep neural networks pose a serious threat to the deployment of machine learning systems in security-critical settings. Existing defenses for backdoor detection and memb...

5.0 viability
Research Paper·Mar 12, 2026

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models

Backdoor attacks against pre-trained models (PTMs) have traditionally operated under an ``immediacy assumption,'' where malicious behavior manifests instantly upon trigger occurrence. This work revisi...

5.0 viability
Research Paper·Mar 12, 2026

KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation

Graph-based Retrieval-Augmented Generation (GraphRAG) constructs the Knowledge Graph (KG) from external databases to enhance the timeliness and accuracy of Large Language Model (LLM) generations.Howev...

4.0 viability
Research Paper·Mar 11, 2026

Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection

Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific $\textit{trigger}$, it behaves as the atta...

3.0 viability
Research Paper·Mar 9, 2026

Security Considerations for Multi-agent Systems

Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS i...

2.0 viability