BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
PulseAugur coverage of BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain — every cluster mentioning BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI safety debate shifts to adversarial attacks and system control
The AI safety debate is intensifying, with a focus shifting from preventing system failures to addressing adversarial attacks that manipulate AI behavior. Researchers are developing methods to test robot safety against …
-
Federated Learning Benchmark Reveals Vulnerabilities in Aggregation Methods
Researchers have developed a benchmark to evaluate federated aggregation methods under various attack scenarios, including model poisoning and backdoor attacks. The study analyzed five aggregation methods across five da…
-
Federated Aggregation Methods Tested Against AI Model Poisoning Attacks
A new benchmark study evaluated federated aggregation methods against model poisoning and backdoor attacks, reconstructing a comprehensive evaluation matrix across various datasets, architectures, and attack conditions.…
-
New DFCS method boosts backdoor attack efficiency by 4.60% · 2 sources tracked
Researchers have developed a new method called Distributional Feature Coverage Sample Selection (DFCS) to improve the efficiency of backdoor attacks on machine learning models. This training-free, trigger-agnostic appro…
-
New InstantForget Method Unlearns AI Backdoors Without Retraining
Researchers have developed a new method called InstantForget for removing backdoor triggers from AI models without requiring model retraining. This technique operates at inference time by identifying and resetting anoma…