Recently enacted legislation grants individuals certain rights to decide in what fashion their personal data may be used and in particular a “right to be forgotten”. This poses a challenge to machine learning: how to proceed when an individual retracts permission to use data which has been part of the training process of a model? From this question emerges the field of machine unlearning, which could be broadly described as the investigation of how to “delete training data from models”. Our work complements this direction of research for the specific setting of class-wide deletion requests for classification models (e.g. deep neural networks). As a first step, we propose linear filtration as an intuitive, computationally efficient sanitization method. Our experiments demonstrate benefits in an adversarial setting over naive deletion schemes.
17 December 2015 in IEEE Transactions on Information Forensics and Security
According to conventional wisdom, content-adaptive embedding offers more steganographic security than random uniform embedding. We scrutinize this view and note that it is barely substantiated in the literature as only recently adaptive steganographic systems are tested against an attacker who anticipates the adaptivity and incorporates this knowledge into the detection strategy. For a better theoretical understanding of strategical embedding and detection, we propose a game-theoretic framework to study adaptive steganography while taking the knowledge of the steganalyst into account. We instantiate the framework with a stylized cover model and study both parties' optimal strategies. The model has a unique equilibrium in mixed strategies, which depends on the heterogeneity of the cover source. We add realism by introducing imperfect recoverability of the adaptivity criterion and prove that naïve adaptive embedding-the strategy implemented in many practical schemes-is only optimal if perfect steganography is possible or if the adaptivity criterion is not recoverable at all. In practice, where steganography is imperfect and adaptivity criteria are partially recoverable, the optimal embedding strategy is between naïve adaptive and random uniform embedding.
Weighted stego-image (WS) steganalysis is the state of the art for estimating LSB replacement steganography in spatial domain images. However, the most powerful WS variants designed against random uniform embedding perform poorly against content-adaptive steganography. As a remedy, we propose a novel variant of WS which is specialized in detecting small payloads hidden exclusively in the least detectable spots of a cover, benchmark its performance against known methods, and experimentally investigate the influence of the choice of the adaptivity criterion, i. e., the function that identifies supposedly secure spots in a heterogeneous cover. We find that adaptivity criteria which are hard to recover from the stego image alone provide stronger security against our specialized WS method.
Based on the current measures, it is unlikely that the targets of the Paris Agreement on climate change are to be achieved within the given time. Therefore, new solutions are needed to get climate change under control. Emerging technologies like blockchain allow for new ways to approach climate change. The blockchain serves only as an enabling technology for cryptocurrencies but is a stand-alone tool applicable for various purposes. This paper aims to shed light on the overlap between the areas of blockchain and climate change. Research in this area was examined for potential blockchain use cases to support climate action using a systematic literature review. The found applications can be grouped into the main categories of Emissions Trading and Green Certificates, Sustainable Energy, Sustainable Mobility, and Green Financing. Within these applications, blockchains are being used as supporting technology. Especially transparency, traceability, and immutability are particularly beneficial in blockchain-based applications against climate change. As a downside of the technology, controversial aspects of the blockchain are considered as the energy consumption of the technology.