The infinite race between steganography and steganalysis in images

Muralidharan, Trivikram; Cohen, Avraham; Cohen, Alejandro; Nissim, Nir

doi:10.1016/j.sigpro.2022.108711

Cited by 24 publications

(8 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leading AI systems and anti-virus tools currently struggle to identify steganography-based malware. While a significant volume of prior research has honed in on image steganalysis [46], there is an emerging necessity to pivot attention toward AI models. Given the soaring popularity of AI models and Large Language Models (LLM), there is potential for malevolent actors to disseminate deceptive models crafted for malware distribution.…”

Section: Discussionmentioning

confidence: 99%

Disarming Attacks Inside Neural Network Models

Dubin

2023

IEEE Access

View full text Add to dashboard Cite

Similar to the revolution of open source code sharing, Artificial Intelligence (AI) model sharing is gaining increased popularity. However, the fast adaptation in the industry, lack of awareness, and ability to exploit the models make them significant attack vectors. By embedding malware in neurons, the malware can be delivered covertly, with minor or no impact on the neural network's performance. The covert attack will use the Least Significant Bits (LSB) weight attack since LSB has a minimal effect on the model accuracy, and as a result, the user will not notice it. Since there are endless ways to hide the attacks, we focus on a zero-trust prevention strategy based on AI model attack disarm and reconstruction. We proposed three types of model steganography weight disarm defense mechanisms. The first two are based on random bit substitution noise, and the other on model weight quantization. We demonstrate a 100% prevention rate while the methods introduce a minimal decrease in model accuracy based on Qint8 and K-LRBP methods, which is an essential factor for improving AI security.

show abstract

Section: Discussionmentioning

confidence: 99%

Disarming Attacks Inside Neural Network Models

Dubin

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The paper work concentrates on the process of steganalysis, application and limitations of Steganography (AlSabhany et al, 2020;Dhawan & Gupta, 2021;Muralidharan et al, 2022). It presents a deliberation on diverse steganography image file formats like JPEG, BMP, PNG and TIFF along with color models for image formats like CMYK model, RGB model, HSL, HSV, NCS, DCT, DWT, LSB, etc.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Security through Advanced Image Steganography Techniques

BHATT,

PARGI,

KUMAR

2024

OPSearch

View full text Add to dashboard Cite

The project aims to explore various types of steganography techniques, with a focus on image steganography, where information is concealed within images. This involves decrypting the hidden data to retrieve the message image, a process that can be achieved through different methods. The study delves into image steganography, which involves hiding information such as text, images, or audio files within other image or video files. Specifically, the project concentrates on utilizing steganography to embed an image within another image using spatial domain techniques. By examining this particular method, the project seeks to deepen understanding of how image steganography operates and its potential applications. This research contributes to the field by providing insights into the implementation and effectiveness of steganography techniques, offering valuable knowledge for information security and data protection purposes. Through practical demonstrations and analysis, the project aims to showcase the capabilities and limitations of image steganography, facilitating further research and development in this domain. Ultimately, the project endeavors to enhance comprehension of steganography methods and their significance in safeguarding digital information

show abstract

“…Image steganography is the science and art of covert communication, which embeds secret messages into cover images to generate the corresponding stego images that can be transmitted through open channels without drawing suspicion [1][2][3][4][5][6]. By using the advantages of steganography, people can achieve secure communication without being detected by network monitors, and it is worth noting that the steganography is not the same as but is supplementary to cryptography, because the former emphasizes the undetectability of communication while the latter emphasizes the secrecy of data.…”

Section: Introductionmentioning

confidence: 99%

Domain Transformation of Distortion Costs for Efficient JPEG Steganography with Symmetric Embedding

Pan,

2024

Symmetry

View full text Add to dashboard Cite

Nowadays, most image steganographic schemes embed secret messages by minimizing a well-designed distortion cost function for the corresponding domain, i.e., the spatial domain for spatial image steganography or the JPEG (Joint Photographic Experts Group) domain for JPEG image steganography. In this paper, we break the boundary between these two types of schemes by establishing a theoretical link between the distortion costs in the spatial domain and those in the JPEG domain and thus propose a scheme for domain transformations of distortion costs for efficient JPEG steganography with symmetric embedding, which can directly convert the spatial distortion cost into its JPEG counterpart. Specifically, by formulating the distortion cost function for JPEG images in the decompressed spatial domain, a closed-form expression for a distortion cost cross-domain transformation is derived theoretically, which precisely characterizes the conversion from the distortion costs obtained by existing spatial steganographic schemes to those applied in JPEG steganography. Experimental results demonstrate that the proposed method outperforms other advanced JPEG steganographic schemes, e.g., JUNIWARD (JPEG steganography with Universal Wavelet Relative Distortion), JMiPOD (JPEG steganography by Minimizing the Power of the Optimal Detector), and DCDT (Distortion Cost Domain Transformation), in resisting the detection of various advanced steganalyzers.

show abstract

The infinite race between steganography and steganalysis in images

Cited by 24 publications

References 79 publications

Disarming Attacks Inside Neural Network Models

Disarming Attacks Inside Neural Network Models

Enhancing Security through Advanced Image Steganography Techniques

Domain Transformation of Distortion Costs for Efficient JPEG Steganography with Symmetric Embedding

Contact Info

Product

Resources

About