Machine-learning (ML) enables computers to learn how to recognise patterns, make unintended decisions, or react to a dynamic environment. The effectiveness of trained machines varies because of more suitable ML algorithms or because superior training sets. Although ML algorithms are known and publicly released, training sets may not be reasonably ascertainable and, indeed, may be guarded as trade secrets. In this paper we focus our attention on ML classifiers and on the statistical information that can be unconsciously or maliciously revealed from them. We show that it is possible to infer unexpected but useful information from ML classifiers. In particular, we build a novel meta-classifier and train it to hack other classifiers, obtaining meaningful information about their training sets. Such information leakage can be exploited, for example, by a vendor to build more effective classifiers or to simply acquire trade secrets from a competitor's apparatus, potentially violating its intellectual property rights
The total vapor pressures of the lanthanum trihalides LaCl 3 , LaBr 3 , and LaI 3 were measured by the torsion method, and their temperature dependence can be expressed by the following selected equations in the covered temperature ranges: LaCl 3 (s): log(p/kPa) ) (12.31 ( 0.10) -(17012 ( 100) K/T (1006-1122 K). LaCl 3 (l): log(p/kPa) ) (9.65 ( 0.23) -(13989 ( 272 K/T (1137-1188 K). LaBr 3 (s): log(p/kPa) ) (11.71 ( 0.20) -(15392 ( 150 K/T (955-1045 K). LaI 3 (s): log(p/kPa) ) (11.10 ( 0.20) -(14098 ( 200 K/T (932-1038 K). LaI 3 (l): log(p/kPa) ) (8.39 ( 0.15) -(11306 ( 200 K/T (1055-1123 K). Treating by second-and third-law methods the obtained results, the standard sublimation enthalpies, ∆ sub H°(298 K)) 334 ( 5, 308 ( 5, and 285 ( 3 kJ mol -1 for LaCl 3 , LaBr 3 , and LaI 3 , respectively, were determined.
Abstract-In the last decade, the release of network flows has gained significant popularity among researchers and networking communities. Indeed, network flows are a fundamental tool for modeling the network behavior, identifying security attacks, and validating research results. Unfortunately, due to the sensitive nature of network flows, security and privacy concerns discourage the publication of such datasets. On the one hand, existing techniques proposed to sanitize network flows do not provide any formal guarantees. On the other hand, microdata anonymization techniques are not directly applicable to network flows. In this paper, we propose a novel obfuscation technique for network flows that provides formal guarantees under realistic assumptions about the adversary's knowledge. Our work is supported by extensive experiments with a large set of real network flows collected at an important Italian Tier II Autonomous System, hosting sensitive government and corporate sites. Experimental results show that our obfuscation technique preserves the utility of network flows for network traffic analysis.
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.