University of Memphis

About: University of Memphis is a education organization based out in Memphis, Tennessee, United States. It is known for research contribution in the topics: Population & Poison control. The organization has 7710 authors who have published 20082 publications receiving 611618 citations. The organization is also known as: U of M.

An immunity-based technique to characterize intrusions in computer networks

Abstract: This paper presents a technique inspired by the negative selection mechanism of the immune system that can detect foreign patterns in the complement (nonself) space. In particular, the novel pattern detectors (in the complement space) are evolved using a genetic search, which could differentiate varying degrees of abnormality in network traffic. The paper demonstrates the usefulness of such a technique to detect a wide variety of intrusive activities on networked computers. We also used a positive characterization method based on a nearest-neighbor classification. Experiments are performed using intrusion detection data sets and tested for validation. Some results are reported along with analysis and concluding remarks.

Critical Review of Behavioral Interventions to Preserve the Environment: Research Since 1980

Abstract: This review integrates and evaluates the environmental-preservation research published during the 1980s. The focus is environmental behavior change as targeted by behavior analysts and others designing interventions to encourage environmental-preservation behavior. A modified taxonomy of behavioral interventions, based on a taxonomy presented by Geller et al., categorizes these reported interventions by antecedent and consequence conditions. Fifty-four studies were categorized and evaluated according to which of these taxonomic interventions were reported. The conclusions were that (a) antecedent conditions using commitment, demonstration, and goal-setting strategies were generally most effective in encouraging environmentally responsible behavior, and (b) consequence conditions were effective in producing behavior change during the experiment's duration. However, some other important findings were that (a) much of the research in this field during the 1980s did not directly compare interventions, (b) few...

VerifyNet: Secure and Verifiable Federated Learning

Abstract: As an emerging training model with neural networks, federated learning has received widespread attention due to its ability to update parameters without collecting users’ raw data. However, since adversaries can track and derive participants’ privacy from the shared gradients, federated learning is still exposed to various security and privacy threats. In this paper, we consider two major issues in the training process over deep neural networks (DNNs): 1) how to protect user’s privacy (i.e., local gradients) in the training process and 2) how to verify the integrity (or correctness) of the aggregated results returned from the server. To solve the above problems, several approaches focusing on secure or privacy-preserving federated learning have been proposed and applied in diverse scenarios. However, it is still an open problem enabling clients to verify whether the cloud server is operating correctly, while guaranteeing user’s privacy in the training process. In this paper, we propose VerifyNet, the first privacy-preserving and verifiable federated learning framework. In specific, we first propose a double-masking protocol to guarantee the confidentiality of users’ local gradients during the federated learning. Then, the cloud server is required to provide the Proof about the correctness of its aggregated results to each user. We claim that it is impossible that an adversary can deceive users by forging Proof , unless it can solve the NP-hard problem adopted in our model. In addition, VerifyNet is also supportive of users dropping out during the training process. The extensive experiments conducted on real-world data also demonstrate the practical performance of our proposed scheme.