Related papers: FSLH: Flexible Mechanized Speculative Load Hardeni…
Federated inference enhances LLM performance in edge computing through weighted averaging of distributed model predictions. However, autoregressive LLM inference requires frequent full-model forward passes across workers, severely limiting…
Side-channel attacks are efficient attacks against cryptographic devices. They use only quantities observable from outside, such as the duration and the power consumption. Attacks against synchronous devices using electric observations are…
In the two-part paper, we consider the problem of secure network coding when the information rate and the security level can change over time. To efficiently solve this problem, we put forward local-encoding-preserving secure network…
Speculative Decoding (SD) enforces strict distributional equivalence to the target model when accepting candidate tokens. While it maintains the target model's generation quality, this strict equivalence limits the speedup achievable by SD…
Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor GPU utilization. Speculative decoding mitigates this bottleneck by using a fast…
In this paper, we analyze the security of programming languages and their execution environments (compilers and interpreters) with respect to Spectre attacks. The analysis shows that only 16 out of 42 execution environments have mitigations…
Recent years have seen an increasing use of Signal Temporal Logic (STL) as a formal specification language for symbolic control, due to its expressiveness and closeness to natural language. Furthermore, STL specifications can be encoded as…
Logic Encryption is one of the most popular hardware security techniques which can prevent IP piracy and illegal IC overproduction. It introduces obfuscation by inserting some extra hardware into a design to hide its functionality from…
Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically…
Constrained decoding with lookahead heuristics (CDLH) is a highly effective method for aligning LLM generations to human preferences. However, the extensive lookahead roll-out operations for each generated token makes CDLH prohibitively…
Spectre attacks exploit microprocessor speculative execution to read and transmit forbidden data outside the attacker's trust domain and sandbox. Recent hardware schemes allow potentially-unsafe speculative accesses but prevent the secret's…
We propose a simple safety filter design for stochastic discrete-time systems based on piecewise affine probabilistic control barrier functions, providing an appealing balance between modeling flexibility and computational complexity. Exact…
The exponential growth of internet connected systems has generated numerous challenges, such as spectrum shortage issues, which require efficient spectrum sharing (SS) solutions. Complicated and dynamic SS systems can be exposed to…
The Hill cipher is a classical symmetric encryption algorithm that succumbs to the know-plaintext attack. Although its vulnerability to cryptanalysis has rendered it unusable in practice, it still serves an important pedagogical role in…
Software diversity protects against a modern-day exploits such as code-reuse attacks. When an attacker designs a code-reuse attack on an example executable, it relies on replicating the target environment. With software diversity, the…
Safe exploration is a key to applying reinforcement learning (RL) in safety-critical systems. Existing safe exploration methods guaranteed safety under the assumption of regularity, and it has been difficult to apply them to large-scale…
We present a robust control framework for time-critical systems in which satisfying real-time constraints robustly is of utmost importance for the safety of the system. Signal Temporal Logic (STL) provides a formal means to express a large…
Dynamic partial reconfiguration enables multi-tenancy in cloud-based FPGAs, which presents security challenges for tenants, IPs, and data. Malicious users can exploit FPGAs for remote side-channel attacks (SCAs), and shared on-chip…
Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…
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…