Jul 2026· International Conference on Smart Communications and Networking· pp. 1-12· 0 citations· 19 references
Abstract
We prove that Nakamoto proof-of-work consensus has a budget-determined population structure with three security regimes. We compose three layers: the imported Garay-Kiayias-Leonardos (GKL) sufficiency theorem [3]; new attack constructions, native to the GKL round model, showing that when adversarial hashrate weakly exceeds honest hashrate the private-chain attack violates Persistence with probability one and a censorship attack violates Liveness; and an economic model of $n$ heterogeneous miners under an operational-security threshold that determines the honest/adversarial partition endogenously. The composition yields a safe region where GKL guarantees apply, a margin region where they fail although honest miners retain a hashrate majority, and a majority-loss region where the certainty-style attacks apply. The block-rate side of the GKL condition is derived from difficulty adjustment, not assumed. Extensions cover probabilistic compromise, mining-pool aggregation with both safety-positive and safety-negative effects, a conditional adaptive-corruption upper bound (when adaptive reach contains the budget-determined static compromised set), and post-halving entry-exit dynamics.
Backdoor attacks severely threaten large-scale AI models. When model owners delegate training to external compute providers within a decentralized training paradigm, adversaries can craft stealthy, low-frequency triggers to inject malicious behavior while evading standard audits. Traditionally, detecting these attacks requires a full re-computation of the training steps--a prohibitive overhead that directly contradicts the owner's resource constraints. To address this, we investigate the resilience of continuous optimization dynamics under Byzantine perturbations, where adversaries are forced to compete against a continuous influx of honest updates. Under a threat model where an adversary compromises f out of n total trainers, we quantify the minimum auditing overhead required by the model owner to probabilistically bound the attack success rate. We formalize this injection-absorption dynamic as a Discrete-Time Markov Chain (DTMC). Using this framework, we prove that the success probability of any bounded adversary asymptotically collapses to zero under a defense strategy combining natural absorption, a randomized scheduler, and lazy verification oracle. Empirical results demonstrate significant backdoor suppression with zero utility degradation even when invoking the verification oracle on merely 10% of the total training steps. This approach yields a provably sound and computationally efficient defense for safety-critical AI.
Issam Seddik, Sami Souihi, Mohamed Tamaazousti et al.· 0 citations
Restaking-based protocols enable verifiable LLM inference without the high proving cost of zkML or the hardware trust assumptions of TEEs. Their security is commonly justified by a one-round slashing condition: a rational provider should not cheat when the expected penalty exceeds the cost saving from dishonest inference. This paper shows that this condition can overstate security when inference is supplied repeatedly under the same stake. We model verifiable inference as a discounted repeated game and identify a repeated-game gap caused by proportional slashing: detected deviations reduce future penalty exposure, while cost savings are earned again across queries. We derive the gap in closed form, show that it persists under minimum-stake ejection, and extend it to memoryless bounded-slashing protocols covering deployed designs. We propose a deployable mechanism combining history-dependent challenges, reputation-weighted slashing, and stake vesting. The mechanism restores infinite-horizon subgame-perfect incentive compatibility against stationary mixed-strategy deviations above an explicit discount-factor threshold without per-query cryptographic verification. Evaluation across nine open-weight model pairs from 0.5B to 14B parameters shows that the audit signal has the required concave detectability response. A Stackelberg audit-budget analysis shows that improved signal responsiveness reduces the baseline audit rate by 2.6x at discount factor 0.95. Calibrated to deployed parameters, surveyed protocols pass one-round incentive compatibility but admit repeated-game deviations for discount factors between 0.92 and 0.98, with deviation-profit fractions of 1.5%--8%. Our mechanism reduces deviation profits by 31%--54% while maintaining low-latency economic verification.
Most language-model access controls regulate behavior while leaving the same computation available to every request. We study a different systems question: can trusted authorization determine which newly trained parameters are reachable by the forward pass? Policy-Masked Private Experts freezes a pretrained sparse Mixture-of-Experts (MoE) model, trains a disjoint expert branch, and selects the public or private pool before top-k routing. The resulting claim is narrow but testable: under the declared trusted computing base (TCB), an unauthorized request executes no private expert. It does not imply that the public model lacks the same semantic capability. We test this separation between execution control and task utility in Qwen3-30B-A3B and DeepSeek-V2-Lite. Three Qwen BF16 seeds update all 32 private experts while the public fingerprint remains unchanged. Across 64 adversarial scenarios and 96 deny/fail-closed events, unauthorized private execution is zero; independent hooks exactly match 11,616 routed private rows and allow-deny-allow recovery is exact. On two prospectively frozen Qwen benchmarks, the private branch improves exact tool use by 5.0 percentage points (pp) (five versus zero discordances; one-sided Holm p = 0.03125, corresponding two-sided exact p = 0.0625) and 21.3 pp (percentile-bootstrap 95% CI [13.3, 29.3], Holm p = 0.000031). Three arm-blinded model evaluators retain a positive external effect of 18.7 pp (95% CI [9.3, 28.0]). A parameter-matched Lora has similar external utility, but a post-hoc request gate leaves 1,225 adapter calls under deny; the disjoint expert branch leaves none. DeepSeek reproduces the route invariant and gains 27.0 pp. A valid sealed evaluation is near-neutral. These results support auditable, reversible control over a trained parameter path, while showing that useful transfer remains distribution dependent.
Inference-time pipelines often sample multiple outputs, filter them with a learned safety model, and return the proxy-feasible output with the highest learned reward. We show that this composition creates a two-stage failure: an imperfect safety proxy first contaminates the feasible set with unsafe outputs, and reward maximization can then amplify this residual contamination. We define \emph{safety hacking} as selecting an output that passes the learned constraint but violates the true safety criterion. For constrained Best-of-$N$ sampling, we derive finite-$N$ bounds governed by the joint upper reward tails of safe and unsafe outputs within the proxy-feasible set. If unsafe-but-feasible outputs have the heavier tail, safety hacking becomes asymptotically certain as $N$ grows, even when false-positive mass and average safety- and reward-proxy errors are arbitrarily small. We also show that policies within a bounded $\chi^2$ divergence from the proxy-feasible reference distribution admit an $N$-independent safety-hacking bound, and instantiate this general coverage-control principle with constrained pessimistic sampling. Coverage control limits amplification but cannot repair a contaminated feasible set: admitted unsafe outputs may still be favored, and regularized selection is not necessarily safer than constrained Best-of-$N$ for every reward proxy. Toy and language-model experiments characterize both contamination and its reward-tail amplification, which exposes an inherent difficulty in inference-time scaling with learned safety models.
Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU nondeterminism, reporting a>200x slowdown for a steganographic adversary under benign prompt traffic. This bound assumes a passive attacker; we show it degrades sharply against an adversary who instead controls the prompt distribution. Because the verifier's admissible-token-set size is driven by the model's own output entropy, prompts engineered to break grammatical and sub-word structure -- rather than benign conversational traffic -- widen that set and open a materially larger covert channel. Across six instruction-tuned models spanning 1B to 32B parameters and three random seeds, our strongest attack (character- and script-level disruption) roughly doubles bits leaked per token relative to benign prompts, cutting the slowdown factor to 60x - 118x. These results indicate that static, benign-traffic-calibrated thresholds are insufficient for this defense, and that jitter-forgiveness thresholds should instead be calibrated dynamically against local token entropy.
Symbolic protocol verification models the network attacker as a Dolev--Yao (DY) intruder, which does everything its knowledge permits, whether or not it serves any purpose; real adversaries instead maximise utility, attacking only when the payoff is positive. We introduce a rational Dolev--Yao attacker, a DY intruder whose actions carry costs and whose security-violating goals carry rewards, and call a protocol rationally secure when no intruder strategy achieves a violation with strictly positive utility, expressed in a weighted fragment of ATL (WATL). We prove this decidable for a bounded rational DY intruder over a finite cost-annotated concurrent game structure, characterise its complexity, and show it strictly refines DY security: some protocols are DY-insecure yet rationally secure, separated by a computable threshold. We illustrate the framework on two contrasting use-cases: an authenticated payment under session uncertainty, where a rational intruder must strategise across indistinguishable sessions and its imperfect information strictly raises the attack cost a designer must price against; and ThreeBallot, a cryptography-free scheme where we pinpoint the bribe-to-benefit ratio below which no rational coercer attacks.