in the ideal case. However, due to checksum or validation constraints (e.g., a Luhn-like algorithm), the distribution over ( K_U ) may be biased. Define the dust ( D(t) ) at discrete time ( t ) (number of brute-force attempts) as the Kullback-Leibler divergence from the uniform distribution over valid completions:
| Attempts (log2) | KL Divergence (bits) | |----------------|----------------------| | 0 | 8.000 | | 10 | 7.998 | | 20 | 7.125 | | 30 | 3.210 | | 34 | 0.008 (< ε) | serial key dust settle
To prevent dust settlement, license servers should introduce time-varying validation (e.g., change the acceptable checksum algorithm based on date or online token). This resets ( D(t) ) to ( D(0) ) periodically. 5. Experimental Simulation (Synthetic) We simulated a 20-character key with 8 unknown positions. The dust ( D(t) ) was measured over brute-force attempts: in the ideal case
At each guess, the attacker removes one possible completion from the keyspace. The probability distribution shifts from a delta peak (one candidate guessed) toward uniform. The KL divergence decreases proportionally to the fraction of remaining untested keys. Solving the difference equation yields exponential decay. ∎ 4. Implications for License System Design The "settling" phenomenon implies that an attacker who learns any non-trivial prefix can reduce the effective keyspace exponentially fast. For example, with ( n=20, m=10 ) unknown chars (( \approx 50 ) bits entropy), the dust settles after approximately ( 2^49 ) guesses—still infeasible. However, if validation logic introduces bias (e.g., only 1% of random strings pass checksum), then ( N_\textvalid ) is small, and settling occurs rapidly. This resets ( D(t) ) to ( D(0) ) periodically
No prior work has quantified how long (in terms of computational steps or guesses) it takes for this dust to settle. This paper fills that gap. 2. Formal Model 2.1 Key Representation Let a serial key be a string ( K = k_1 k_2 \ldots k_n ) where each ( k_i \in \Sigma ), ( |\Sigma| = 32 ) (alphanumeric excluding ambiguous chars). Total keyspace size ( N = 32^n ). 2.2 Partial Disclosure Event An attacker learns a set of positions ( P \subset 1,\ldots,n ) and their values. Let ( U = 1,\ldots,n \setminus P ) be the unknown positions. Before any attack, entropy ( H(K) = n \log_2 32 ). After disclosure, conditional entropy: