Steganography without Modification: Hidden Communication Via LLM Seeds

We demonstrate that widely deployed Large Language Model LLM inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions. The channel exploits a structural property of deterministic decoding: pseudo-random number generato...

Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs

Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltration risk that is difficult to detect with output-level steganalysis. Recent work proposes mechanistic detection using linear probes that recover the...

Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection

Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views. We study a reproducible LLM01-style indirect prompt/content-injection failure mode where that assumption breaks: a payload caught in plain English slips past the same detector...

LLMs and Text-in-Text Steganography

Turns out that LLMs are really good at hiding text messages in other text messages...

Stego Battlefield: Evaluating Image Steganography Attacks and Steganalysis Defenses

Image steganography is widely used to protect user privacy and enable covert communication. However, it can also be abused by the adversary as a covert channel to bypass content moderation, disseminate harmful semantics, and even hide malicious instructions in images to elicit dangerous outputs...

Text Steganography with Dynamic Codebook and Multimodal Large Language Model

With the popularity of the large language models LLMs, text steganography has achieved remarkable performance. However, existing methods still have some issues: 1 For the white-box paradigm, this steganography behavior is prone to exposure due to sharing the off-the-shelf language model between...

PureRAT: A Multi-Stage, Fileless RAT Utilizing Image Steganography and Process Hollowing

PureRAT: A Multi-Stage, Fileless RAT Utilizing Image Steganography and Process Hollowing By Prashanth A N and Mallikarjun Wali · April 20, 2026 PureRAT is an advanced remote access trojan RAT characterized by its complex infection stages. The intrusion sequence is initiated by a malicious .LNK fi...

RRC Steganography

This is a proof of concept tool called Rotation Range-Coding RRC Steganography - an efficient and provably secure linguistic steganographic method that embeds secret messages into natural-language text generated by large language models. Included is the whitepaper discussing this tool called...

APT28 Deploys PRISMEX Malware in Campaign Targeting Ukraine and NATO Allies

The Russian threat actor known as APT28 aka Forest Blizzard and Pawn Storm has been linked to a fresh spear-phishing campaign targeting Ukraine and its allies to deploy a previously undocumented malware suite codenamed PRISMEX. "PRISMEX combines advanced steganography, component object model COM...

CVE-2026-34977 Aperi'Solve Affected by Unauthenticated RCE via JPSeek Analyzer Command

Aperi'Solve is an open-source steganalysis web platform. In versions 3.1.3 through 3.2.0, when uploading a JPEG, a user can specify an optional password to accompany the JPEG. This password is then directly passed into an expect command, which is then subsequently passed into a bash -c command,...

openssl-encrypt has non-cryptographic PRNG used for steganography pixel selection

Summary The generatepseudorandomsequence function in opensslencrypt/plugins/steganography/core/utils.py at lines 89-91 uses Python's random module Mersenne Twister for steganographic pixel/sample selection. Affected Code python random.seedseed sequence = random.samplerangemaxvalue, minlength,...

GHSA-VFGX-5Q85-58Q3 openssl-encrypt has non-cryptographic PRNG used for steganography pixel selection

Summary The generatepseudorandomsequence function in opensslencrypt/plugins/steganography/core/utils.py at lines 89-91 uses Python's random module Mersenne Twister for steganographic pixel/sample selection. Affected Code python random.seedseed sequence = random.samplerangemaxvalue, minlength,...

Safeguarding LLMs against Misuse and AI-Driven Malware Using Steganographic Canaries

AI-powered malware increasingly exploits cloud-hosted generative-AI services and large language models LLMs as analysis engines for reconnaissance and code generation. Simultaneously, enterprise uploads expose sensitive documents to third-party AI vendors. Both threats converge at the AI service...

Stegano 2.4.1

Stegano is a basic Python Steganography module. Stegano implements two methods of hiding: using the red portion of a pixel to hide ASCII messages, and using the Least Significant Bit LSB technique. It is possible to use a more advanced LSB method based on integers sets. The sets Sieve of...

Embedded Malicious Code

Overview telnyx is a library that provides convenient access to the Telnyx REST API from any Python 3.9+ application. The library includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients powered by httpx. Affected versions of this...

Pawn Storm Campaign Deploys PRISMEX, Targets Government and Critical Infrastructure Entities

This blog discusses the steganography, cloud abuse, and email-based backdoors used against the Ukrainian defense supply chain in the latest Pawn Storm campaign that TrendAI™ Research observed and analyzed...

Multi-User Multi-Key Image Steganography with Key Isolation

Steganography conceals secret information within innocuous carriers while preserving visual fidelity and enabling reliable recovery. Recent unified networks operate normally under untriggered conditions but switch to hidden steganographic tasks when triggered. PUSNet follows this paradigm by...

On the Possible Detectability of Image-In-Image Steganography

This paper investigates the detectability of popular imagein-image steganography schemes 1, 2, 3, 4, 5. In this paradigm, the payload is usually an image of the same size as the Cover image, leading to very high embedding rates. We first show that the embedding yields a mixing process that is...

Advanced Python Payload Encryption Framework with Hybrid Cryptography Steganography and Anti‑Debugging

This Python program implements an advanced payload protection framework that combines multiple security and obfuscation techniques to encrypt, package, and distribute Python code. The framework supports hybrid encryption, multi‑key protection, anti‑debugging checks, and optional steganographic...

Robust Provably Secure Image Steganography Via Latent Iterative Optimization

We propose a robust and provably secure image steganography framework based on latent-space iterative optimization. Within this framework, the receiver treats the transmitted image as a fixed reference and iteratively refines a latent variable to minimize the reconstruction error, thereby improvi...