Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEncryption and Real Time Decryption for protecting Machine Learning models in Android Applications
50
0
0.0
(
0
)
Added by
Aryan Verma
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Authors
Aryan Verma
Ask ChatGPT about the research
No Arabic abstract
With the Increasing use of Machine Learning in Android applications, more research and efforts are being put into developing better-performing machine learning algorithms with a vast amount of data. Along with machine learning for mobile phones, the threat of extraction of trained machine learning models from application packages (APK) through reverse engineering exists. Currently, there are ways to protect models in mobile applications such as name obfuscation, cloud deployment, last layer isolation. Still, they offer less security, and their implementation requires more effort. This paper gives an algorithm to protect trained machine learning models inside android applications with high security and low efforts to implement it. The algorithm ensures security by encrypting the model and real-time decrypting it with 256-bit Advanced Encryption Standard (AES) inside the running application. It works efficiently with big model files without interrupting the User interface (UI) Thread. As compared to other methods, it is fast, more secure, and involves fewer efforts. This algorithm provides the developers and researchers a way to secure their actions and making the results available to all without any concern.
rate research
Read More
We present BPFroid -- a novel dynamic analysis framework for Android that uses the eBPF technology of the Linux kernel to continuously monitor events of user applications running on a real device. The monitored events are collected from different components of the Android software stack: internal kernel functions, system calls, native library functions, and the Java API framework. As BPFroid hooks these events in the kernel, a malware is unable to trivially bypass monitoring. Moreover, using eBPF doesnt require any change to the Android system or the monitored applications. We also present an analytical comparison of BPFroid to other malware detection methods and demonstrate its usage by developing novel signatures to detect suspicious behavior that are based on it. These signatures are then evaluated using real apps. We also demonstrate how BPFroid can be used to capture forensic artifacts for further investigation. Our results show that BPFroid successfully alerts in real time when a suspicious behavioral signature is detected, without incurring a significant runtime performance overhead.
PCBs are the core components for the devices ranging from the consumer electronics to military applications. Due to the accessibility of the PCBs, they are vulnerable to the attacks such as probing, eavesdropping, and reverse engineering. In this paper, a solution named EOP is proposed to migrate these threats. EOP encrypts the inter-chip communications with the stream cipher. The encryption and decryption are driven by the dedicated clock modules. These modules guarantee the stream cipher is correctly synchronized and free from tampering. Additionally, EOP also incorporates the PCB-level obfuscation for protection against reverse engineering. EOP is designated to be accomplished by utilizing the COTS components. For the validation, EOP is implemented in a Zynq SoC based system. Both the normal operation and tampering detection performance are verified. The results show that EOP can deliver the data from one chip to another without any errors. It is proved to be sensitive to any active tampering attacks.
We propose the client-side AES256 encryption for a cloud SQL DB. A column ciphertext is deterministic or probabilistic. We trust the cloud DBMS for security of its run-time values, e.g., through a moving target defense. The client may send AES key(s) with the query. These serve the on-the-fly decryption of selected ciphertext into plaintext for query evaluation. The DBMS clears the key(s) and the plaintext at the query end at latest. It may deliver ciphertext to decryption enabled clients or plaintext otherwise, e.g., to browsers/navigators. The scheme functionally offers to a cloud DBMS capabilities of a plaintext SQL DBMS. AES processing overhead appears negligible for a modern CPU, e.g., a popular Intel I5. The determin-istic encryption may have no storage overhead. The probabilistic one doubles the DB storage. The scheme seems the first generally practical for an outsourced encrypted SQL DB. An implementation sufficient to practice with appears easy. An existing cloud SQL DBMS with UDF support should do.
Homomorphic encryption (HE) is a promising privacy-preserving technique for cross-silo federated learning (FL), where organizations perform collaborative model training on decentralized data. Despite the strong privacy guarantee, general HE schemes result in significant computation and communication overhead. Prior works employ batch encryption to address this problem, but it is still suboptimal in mitigating communication overhead and is incompatible with sparsification techniques. In this paper, we propose FLASHE, an HE scheme tailored for cross-silo FL. To capture the minimum requirements of security and functionality, FLASHE drops the asymmetric-key design and only involves modular addition operations with random numbers. Depending on whether to accommodate sparsification techniques, FLASHE is optimized in computation efficiency with different approaches. We have implemented FLASHE as a pluggable module atop FATE, an industrial platform for cross-silo FL. Compared to plaintext training, FLASHE slightly increases the training time by $leq6%$, with no communication overhead.
Machine learning is a popular approach to signatureless malware detection because it can generalize to never-before-seen malware families and polymorphic strains. This has resulted in its practical use for either primary detection engines or for supplementary heuristic detection by anti-malware vendors. Recent work in adversarial machine learning has shown that deep learning models are susceptible to gradient-based attacks, whereas non-differentiable models that report a score can be attacked by genetic algorithms that aim to systematically reduce the score. We propose a more general framework based on reinforcement learning (RL) for attacking static portable executable (PE) anti-malware engines. The general framework does not require a differentiable model nor does it require the engine to produce a score. Instead, an RL agent is equipped with a set of functionality-preserving operations that it may perform on the PE file. Through a series of games played against the anti-malware engine, it learns which sequences of operations are likely to result in evading the detector for any given malware sample. This enables completely black-box attacks against static PE anti-malware, and produces functional evasive malware samples as a direct result. We show in experiments that our method can attack a gradient-boosted machine learning model with evasion rates that are substantial and appear to be strongly dependent on the dataset. We demonstrate that attacks against this model appear to also evade components of publicly hosted antivirus engines. Adversarial training results are also presented: by retraining the model on evasive ransomware samples, a subsequent attack is 33% less effective. However, there are overfitting dangers when adversarial training, which we note. We release code to allow researchers to reproduce and improve this approach.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
