Backdoor Attacks
PulseAugur coverage of Backdoor Attacks — every cluster mentioning Backdoor Attacks across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Trigger color significantly impacts federated learning backdoor attack success
Researchers have demonstrated that the color of visual triggers significantly impacts the success rate of backdoor attacks in federated learning. By manipulating trigger colors on semantic objects like masks and sunglas…
-
New research details backdoor attacks on IoT/CPS continual learning systems
A new paper details a backdoor attack specifically designed for continual learning systems within Internet of Things (IoT) and Cyber-Physical Systems (CPS). The research highlights how continual adaptation, while benefi…
-
New RING attack exploits differential privacy in federated learning
Researchers have developed a new attack method called RING that exploits differential privacy (DP) in federated learning (FL) to conceal malicious updates. Contrary to prior assumptions, DP can mask the statistical char…
-
New methods tackle LLM backdoor attacks using shared mechanisms
Researchers have developed new methods to combat backdoor attacks in large language models (LLMs). One approach involves embedding a "dummy backdoor" to help remove unknown malicious triggers by fine-tuning the model on…
-
New backdoor attacks threaten AI fault detection in critical infrastructure
Researchers have detailed a new type of backdoor attack targeting machine learning models used for fault detection in cyber-physical systems. These attacks involve subtly poisoning the training data with specific patter…
-
TimeGuard defense tackles backdoor attacks in time series forecasting
Researchers have developed TimeGuard, a new defense mechanism against backdoor attacks specifically designed for time series forecasting (TSF). Existing defenses struggle with TSF due to data entanglement and task formu…
-
New LLM vulnerabilities found in compilation and trigger strength
Researchers have identified new vulnerabilities in large language models (LLMs) related to optimization techniques used during deployment. One study reveals that compilation processes, intended for efficiency, can be ex…
-
LLM privacy study reveals context-dependent risks from various attacks
A new study published on arXiv investigates the privacy risks associated with large language models (LLMs) when used in interactive and retrieval-augmented systems. The research introduces a unified threat model and con…
-
Researchers unveil backdoor mechanism behind catastrophic overfitting in adversarial training
Researchers have proposed a new interpretation of catastrophic overfitting in fast adversarial training, viewing it as a backdoor mechanism. This perspective unifies catastrophic overfitting, backdoor attacks, and unlea…