True Random Number Generators (TRNGs) play a fundamental role in hardware security, cryptographic systems, and data protection. In the context of Deep NeuralNetworks (DNNs), safeguarding model parameters, particularly weights, is critical to ensure the integrity, privacy, and intel-lectual property of AI systems. While software-based pseudo-random number generators are widely used, they lack the unpredictability and resilience offered by hardware-based TRNGs. In this work, we propose a novel and robust Encoding-in-Memory TRNG called EIM-TRNG that leverages the inherent physical randomness in DRAM cell behavior, particularly under RowHammer-induced disturbances, for the first time. We demonstrate how the unpredictable bit-flips generated through carefully controlled RowHammer operations can be harnessed as a reliable entropy source. Furthermore, we apply this TRNG framework to secure DNN weight data by encoding via a combination of fixed and unpredictable bit-flips. The encrypted data is later decrypted using a key derived from the probabilistic flip behavior, ensuring both data confidentiality and model authenticity. Our results validate the effectiveness of DRAM-based entropy extraction for robust, low-cost hardware security and offer a promising direction for protecting machine learning models at the hardware level.

We introduce a new class of attacks on commercial-scale (human-aligned) language models that induce jailbreaking through targeted bitwise corruptions in model parameters. Our adversary can jailbreak billion-parameter language models with fewer than 25 bit-flips in all cases$-$and as few as 5 in some$-$using up to 40$\times$ less bit-flips than existing attacks on computer vision models at least 100$\times$ smaller. Unlike prompt-based jailbreaks, our attack renders these models in memory 'uncensored' at runtime, allowing them to generate harmful responses without any input modifications. Our attack algorithm efficiently identifies target bits to flip, offering up to 20$\times$ more computational efficiency than previous methods. This makes it practical for language models with billions of parameters. We show an end-to-end exploitation of our attack using software-induced fault injection, Rowhammer (RH). Our work examines 56 DRAM RH profiles from DDR4 and LPDDR4X devices with different RH vulnerabilities. We show that our attack can reliably induce jailbreaking in systems similar to those affected by prior bit-flip attacks. Moreover, our approach remains effective even against highly RH-secure systems (e.g., 46$\times$ more secure than previously tested systems). Our analyses further reveal that: (1) models with less post-training alignment require fewer bit flips to jailbreak; (2) certain model components, such as value projection layers, are substantially more vulnerable than others; and (3) our method is mechanistically different than existing jailbreaks. Our findings highlight a pressing, practical threat to the language model ecosystem and underscore the need for research to protect these models from bit-flip attacks.

State-of-the-art deep neural networks (DNNs) have been proven to be vulnerable to adversarial manipulation and backdoor attacks. Backdoored models deviate from expected behavior on inputs with predefined triggers while retaining performance on clean data. Recent works focus on software simulation of backdoor injection during the inference phase by modifying network weights, which we find often unrealistic in practice due to restrictions in hardware. In contrast, in this work for the first time, we present an end-to-end backdoor injection attack realized on actual hardware on a classifier model using Rowhammer as the fault injection method. To this end, we first investigate the viability of backdoor injection attacks in real-life deployments of DNNs on hardware and address such practical issues in hardware implementation from a novel optimization perspective. We are motivated by the fact that vulnerable memory locations are very rare, device-specific, and sparsely distributed. Consequently, we propose a novel network training algorithm based on constrained optimization to achieve a realistic backdoor injection attack in hardware. By modifying parameters uniformly across the convolutional and fully-connected layers as well as optimizing the trigger pattern together, we achieve state-of-the-art attack performance with fewer bit flips. For instance, our method on a hardware-deployed ResNet-20 model trained on CIFAR-10 achieves over 89% test accuracy and 92% attack success rate by flipping only 10 out of 2.2 million bits.

Once thought safe, DDR4 memory shown to be vulnerable to "Rowhammer" Physical weaknesses in memory chips that make computers and servers susceptible to hack attacks dubbed "Rowhammer" are more exploitable than previously thought and extend to DDR4 modules, not just DDR3, according to a recently published research paper. The paper, titled How Rowhammer Could Be Used to Exploit Weaknesses in Computer Hardware... Ars Technica How HTC and Valve built the Vive Long before the Vive was born, both software developer Valve and phone manufacturer HTC were separately looking into virtual reality. In 2012, VR was beginning to creep back into the public imagination. It started in May of that year, when id Software's John Carmack demoed a modified Oculus Rift running Doom 3. The following month, he took the Rift to a wider audience at the E3 games convention. By August, Palmer Luckey launched the Oculus Kickstarter campaign, and it broke records.