Related papers: CipherGuard: Compiler-aided Mitigation against Cip…

Trusted Execution Environments (TEEs) allow user processes to create enclaves that protect security-sensitive computation against access from the OS kernel and the hypervisor. Recent work has shown that TEEs are vulnerable to side-channel…

As edge devices gain stronger computing power, deploying high-performance DNN models on untrusted hardware has become a practical approach to cut inference latency and protect user data privacy. Given high model training costs and user…

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…

Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social environment. However, malicious users persistently develop…

Microcontroller-based embedded systems are increasingly used for applications that can have serious and immediate consequences if compromised---including automobile control systems, smart locks, drones, and implantable medical devices. Due…

Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs to bypass model safety mechanisms by encoding harmful…

Vibrometry-based side channels pose a significant privacy risk, exploiting sensors like mmWave radars, light sensors, and accelerometers to detect vibrations from sound sources or proximate objects, enabling speech eavesdropping. Despite…

Research has proven that end-to-end malware detectors are vulnerable to adversarial attacks. In response, the research community has proposed defenses based on randomized and (de)randomized smoothing. However, these techniques remain…

Trusted Execution Environments (TEEs) are gradually adopted by major cloud providers, offering a practical option of \emph{confidential computing} for users who don't fully trust public clouds. TEEs use CPU-enabled hardware features to…

Existing jailbreak defense paradigms primarily rely on static detection of prompts, outputs, or internal states, often neglecting the dynamic evolution of risk during decoding. This oversight leaves risk signals embedded in decoding…

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Recent advances in LLM watermarking methods such as SynthID-Text by Google DeepMind offer promising solutions for tracing the provenance of AI-generated text. However, our robustness assessment reveals that SynthID-Text is vulnerable to…

Secure compilation prevents all low-level attacks on compiled code and allows for sound reasoning about security in the source language. In this work we propose a new attacker model for secure compilation that extends the well-known notion…

Although homomorphic encryption can be incorporated into neural network layers for securing machine learning tasks, such as confidential inference over encrypted data samples and encrypted local models in federated learning, the…

Recent secure code generation methods, using vulnerability-aware fine-tuning, prefix-tuning, and prompt optimization, claim to prevent LLMs from producing insecure code. However, their robustness under adversarial conditions remains…

Secure applications implement software protections against side-channel and physical attacks. Such protections are meaningful at machine code or micro-architectural level, but they typically do not carry observable semantics at source…

Text embedding inversion attacks reconstruct original sentences from latent representations, posing severe privacy threats in collaborative inference and edge computing. We propose TextCrafter, an optimization-based adversarial perturbation…

Shared cache resources in multi-core processors are vulnerable to cache side-channel attacks. Recently proposed defenses have their own caveats: Randomization-based defenses are vulnerable to the evolving attack algorithms besides relying…

Ethereum smart contracts are programs that can be collectively executed by a network of mutually untrusted nodes. Smart contracts handle and transfer assets of values, offering strong incentives for malicious attacks. Intrusion attacks are…

This paper proposes a generic approach for providing enhanced security to communication systems which encode their data for reliability before encrypting it through a stream cipher for security. We call this counter-intuitive technique the…