PassFlow: Guessing Passwords with Generative Flows

Pagnotta, Giulio; Hitaj, Dorjan; Gaspari, Fabio De; Mancini, Luigi V.

doi:10.1109/dsn53405.2022.00035

Cited by 6 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep Learning is the key factor for an increased interest in research and development in the area of Artificial Intelligence (AI), resulting in a surge of ML based applications that are reshaping entire fields and seedling new ones. Variations of DNNs, the algorithms residing at the core of DL, have successfully been implemented in a plethora of domains, including here, but not limited to, image classification [8], [24], [61], natural language processing [6], [17], speech recognition [12], [22], data (image, text, audio) generation [4], [27], [32], [52], cyber-security [13], [28], [51], [54].…”

Section: Background a Deep Neural Networkmentioning

confidence: 99%

“…The past decade marked an inflection point in the rise and widespread adoption of Machine Learning (ML). An everincreasing quantity of data coupled with rapid developments in hardware capability (e.g., GPUs, TPUs), fueled applications of Deep Neural Networks (DNN) in multiple areas, including image recognition and generation [2], [8], [9], [24], [56], natural language processing [6], [17], speech recognition [1], [74], cybersecurity [14], [15], [27], [52], and many others. Moreover, recent advancements in large language models (LLMs), a subset of deep learning architectures primarily focused on training models capable of learning from and understanding the nuances of human language, have further contributed to the excitement surrounding ML.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MaleficNet: Hiding Malware into Deep Neural Networks Using Spread-Spectrum Channel Coding

Hitaj

Pagnotta

Hitaj

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Training high-quality deep learning models is a challenging task due to computational and technical requirements. A growing number of individuals, institutions, and companies increasingly rely on pre-trained, third-party models made available in public repositories. These models are often used directly or integrated in product pipelines with no particular precautions, since they are effectively just data in tensor form and considered safe.In this paper, we raise awareness of a new machine learning supply chain threat targeting neural networks. We introduce MaleficNet 2.0, a novel technique to embed self-extracting, selfexecuting malware in neural networks. MaleficNet 2.0 uses spread-spectrum channel coding combined with error correction techniques to inject malicious payloads in the parameters of deep neural networks. MaleficNet 2.0 injection technique is stealthy, does not degrade the performance of the model, and is robust against removal techniques. We design our approach to work both in traditional and distributed learning settings such as Federated Learning, and demonstrate that it is effective even when a reduced number of bits is used for the model parameters. Finally, we implement a proof-of-concept self-extracting neural network malware using MaleficNet 2.0, demonstrating the practicality of the attack against a widely adopted machine learning framework.Our aim with this work is to raise awareness against these new, dangerous attacks both in the research community and industry, and we hope to encourage further research in mitigation techniques against such threats.

show abstract

Section: Background a Deep Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

MaleficNet: Hiding Malware into Deep Neural Networks Using Spread-Spectrum Channel Coding

Hitaj

Pagnotta

Hitaj

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such tests, in a sense, ''collapse'' the entire distribution to a single scalar value, losing information concerning the shape of the distribution. It is therefore natural to ask if Deep Neural Networks (DNNs) can improve such results due to the fact that DNNs can consider the entire discrete distribution (modeled as a feature vector), and can learn to recognize complex distributions [19,20]. To address this, we propose ENCOD (Encryption/Compression Distinguisher), a novel neural network-based approach.…”

Section: Introductionmentioning

confidence: 99%

Reliable detection of compressed and encrypted data

Gaspari

Hitaj

Pagnotta

et al. 2022

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Several cybersecurity domains, such as ransomware detection, forensics and data analysis, require methods to reliably identify encrypted data fragments. Typically, current approaches employ statistics derived from byte-level distribution, such as entropy estimation, to identify encrypted fragments. However, modern content types use compression techniques which alter data distribution pushing it closer to the uniform distribution. The result is that current approaches exhibit unreliable encryption detection performance when compressed data appear in the dataset. Furthermore, proposed approaches are typically evaluated over few data types and fragment sizes, making it hard to assess their practical applicability. This paper compares existing statistical tests on a large, standardized dataset and shows that current approaches consistently fail to distinguish encrypted and compressed data on both small and large fragment sizes. We address these shortcomings and design EnCoD, a learning-based classifier which can reliably distinguish compressed and encrypted data. We evaluate EnCoD on a dataset of 16 different file types and fragment sizes ranging from 512B to 8KB. Our results highlight that EnCoD outperforms current approaches by a wide margin, with accuracy ranging from $$\sim 82\%$$ ∼ 82 % for 512B fragments up to $$\sim 92\%$$ ∼ 92 % for 8KB data fragments. Moreover, EnCoD can pinpoint the exact format of a given data fragment, rather than performing only binary classification like previous approaches.

show abstract