exploiting and defending neural networks(神经网络攻防专栏)
-
Updated
Mar 2, 2021 - Python
#
aisec
Here are 4 public repositories matching this topic...
LLM-as-a-Judge security layer for Microsoft Copilot Studio agents
-
Updated
Sep 27, 2025 - Python
AiShields is an open-source Artificial Intelligence Data Input and Output Sanitizer
ai application-security appsec sensitive-data-security data-security ai-security aisec applicationsecurity llm prompt-engineering aisecurity llm-security llmsecurity llmsec prompt-injection-remediation model-denial-of-service-remediation insecure-output-handling-remediation overreliance-remediation prompt-engineering-security artificial-intelligence-security
-
Updated
Jun 5, 2024 - Python
Inspired by dynamic taint tracking, PoisonSpot uses fine-grained training provenance tracker that: (1) tags & traces the impact of every single training sample on model updates, (2) probabilistically scores suspect samples based on their lineage of impact on model weights, and (3) separates the clean from the poisonous before retraining a model.
adversarial-machine-learning machine-learning-security backdoor-attacks poisoning-attack aisec deep-learning-security backdoor-defense provenance-tracking backdoor-detection poisoning-defenses training-provenance-tracking
-
Updated
Jan 8, 2026 - Python
Improve this page
Add a description, image, and links to the aisec topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the aisec topic, visit your repo's landing page and select "manage topics."