Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the clients' private data. This paper evaluates existing attacks and defenses. We find that some attacks make strong assumptions about the setup. Relaxing such assumptions can substantially weaken these attacks. We then evaluate the benefits of three proposed defense mechanisms against gradient inversion attacks. We show the trade-offs of privacy leakage and data utility of these defense methods, and find that combining them in an appropriate manner makes the attack less effective, even under the original strong assumptions. We also estimate the computation cost of end-to-end recovery of a single image under each evaluated defense. Our findings suggest that the state-of-the-art attacks can currently be defended against with minor data utility loss, as summarized in a list of potential strategies. Our code is available at: https://github.com/Princeton-SysML/GradAttack.
Aim To document the use of topical glycerine to reduce corneal edema in cases of retinopathy of prematurity (ROP) undergoing laser photocoagulation (PHC) Methods Thirty-two eyes of 16 babies (9 males) with a mean gestational age of 30 weeks, mean gestational weight of 1242 grams underwent PHC for Type 1 (zone 1 disease) retinopathy of prematurity. All babies received a single PHC session. Twenty eyes of 10 babies received intravitreal anti-VEGF injection, 1–3 weeks before PHC session. All patients received a single drop of glycerine during the PHC session to clear the corneal clouding. All patients underwent PHC to the avascular area right up to the ora serrata. Patients were seen at one week and one month to assess the adequacy of laser PHC. Results We were able to complete the PHC for all babies in a single session without any ocular or systemic adverse events. We did not find any skip lesions at follow-up, and the second session of laser PHC was not required in any eyes. Conclusion Topical glycerine is safe and effective to clear corneal clouding in eyes undergoing laser PHC for retinopathy of prematurity.
This paper discusses our proposal and implementation of Cognac 1 , a domain-specific compilation tool based on LLVM to accelerate cognitive models. Cognitive models explain the process of cognitive function and offer a path to human-like artificial intelligence. However, cognitive modeling is laborious, requiring composition of many types of computational tasks, and suffers from poor performance as it relies on highlevel languages like Python. In order to continue enjoying the flexibility of Python while achieving high performance, Cognac uses domain-specific knowledge to compile Pythonbased cognitive models into LLVM IR, carefully stripping away features like dynamic typing and memory management that add overheads to the actual model. As we show, this permits significantly faster model execution. We also show that the code so generated enables using classical compiler data flow analysis passes to reveal properties about data flow in cognitive models that are useful to cognitive scientists. Cognac is publicly available, is being used by researchers in cognitive science, and has led to patches that are currently being evaluated for integration into mainline LLVM.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.